Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 94805
    Prev
    Next
    INDEX
    Explanations

    he

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     completely
    -0.06
     Bamboo
    -0.06
    ETING
    -0.06
     by
    -0.06
    Hopefully
    -0.06
     admittedly
    -0.06
     Figures
    -0.06
     rotate
    -0.06
    :-
    -0.06
    …
    -0.06
    POSITIVE LOGITS
    _long
    0.07
    .runner
    0.07
    .readLine
    0.07
    สำเร
    0.06
    dığını
    0.06
    (Expected
    0.06
     var
    0.06
    vation
    0.06
    LayoutManager
    0.06
    _Box
    0.06
    Activations Density 0.228%

    No Known Activations