© 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
    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. 73773
    Prev
    Next
    INDEX
    Explanations

    commas brackets

    np_max-act · gemini-2.0-flash

    The neuron responds to mentions of analytical or measurement methods and technical procedures in scientific text.

    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
     MAS
    -0.07
     那
    -0.07
     TRE
    -0.06
     incorrectly
    -0.06
    ΥΣ
    -0.06
    ADC
    -0.06
     Mills
    -0.06
     HMS
    -0.06
     カ
    -0.06
     ミ
    -0.06
    POSITIVE LOGITS
    的问题
    0.07
    blend
    0.07
     bitten
    0.06
    вич
    0.06
     Final
    0.06
     trụ
    0.06
    年代
    0.06
    �
    0.06
     hiểm
    0.06
    _logo
    0.06
    Activations Density 0.050%

    No Known Activations