© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 58055
    Prev
    Next
    INDEX
    Explanations

    Citations

    np_max-act · gemini-2.0-flash

    references to the ecological and biological importance of various species and their interactions within ecosystems.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron responds to numeric tokens—especially the decimal‐formatted reference indices and other numbers embedded in citation brackets.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    职业
    -0.07
     china
    -0.07
     NT
    -0.06
    铺
    -0.06
     statutory
    -0.06
     himself
    -0.06
    十八
    -0.06
    culate
    -0.06
    getStringExtra
    -0.06
    odcast
    -0.06
    POSITIVE LOGITS
    	Model
    0.07
     فراهم
    0.07
    simd
    0.06
     hủy
    0.06
    _TRACE
    0.06
     starch
    0.06
    _EVAL
    0.06
    _matrices
    0.06
     datatable
    0.06
     competitors
    0.06
    Activations Density 0.008%

    No Known Activations