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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 126678
    Prev
    Next
    INDEX
    Explanations

    light

    np_max-act · gemini-2.0-flash

    The neuron activates for mentions of light and related optical or electromagnetic radiation terms.

    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
    adata
    -0.07
    ottom
    -0.07
    amil
    -0.07
    하나
    -0.06
    //#
    -0.06
    customerId
    -0.06
    (Canvas
    -0.06
     cáo
    -0.06
     gazet
    -0.06
    avn
    -0.06
    POSITIVE LOGITS
     parliament
    0.08
     light
    0.07
     troops
    0.07
    _LINE
    0.07
     lda
    0.07
     chemotherapy
    0.06
     blockSize
    0.06
    _TIMES
    0.06
     Cutting
    0.06
    侯
    0.06
    Activations Density 0.012%

    No Known Activations