© 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. 15-RESID-POST-AA
    6. 23962
    Prev
    Next
    INDEX
    Explanations

    code

    np_max-act · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    -js
    -0.06
     上
    -0.06
     AK
    -0.06
     Hemisphere
    -0.06
    怖
    -0.06
    后
    -0.06
     decorations
    -0.06
     irresponsible
    -0.06
     PNG
    -0.06
     terrified
    -0.06
    POSITIVE LOGITS
     Von
    0.08
    炮
    0.07
    _neurons
    0.07
     controlId
    0.06
    .aspect
    0.06
     vliv
    0.06
     karış
    0.06
     बस
    0.06
    @endsection
    0.06
     області
    0.06
    Activations Density 0.276%

    No Known Activations