© 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. 19-RESID-POST-AA
    6. 127191
    Prev
    Next
    INDEX
    Explanations

    Code/Programming

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     čím
    -0.06
     เก
    -0.06
     *↵
    -0.06
    entication
    -0.06
    уд
    -0.06
    後に
    -0.06
    roof
    -0.05
     blended
    -0.05
    .SingleOrDefault
    -0.05
     Wyn
    -0.05
    POSITIVE LOGITS
     Gl
    0.07
    .Instance
    0.07
    .Perform
    0.07
    CppObject
    0.06
     regimes
    0.06
    Iterations
    0.06
    :UIControlState
    0.06
     hn
    0.06
    _segment
    0.06
     NL
    0.06
    Activations Density 0.000%

    No Known Activations