© 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 (Instruct)
    7. Resid Post - 131k
    9. 23-RESID-POST-AA
    11. 7636
    Prev
    Next
    INDEX
    Explanations

    activism and protests

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    orce
    -0.07
    рю
    -0.06
     Target
    -0.06
    読
    -0.06
    _variables
    -0.06
    -In
    -0.06
     SQUARE
    -0.06
     brides
    -0.06
     Rotary
    -0.06
    ----------------------------------------------------------------------↵
    -0.06
    POSITIVE LOGITS
     nk
    0.07
    icionar
    0.07
     minX
    0.06
    leon
    0.06
    igar
    0.06
    mits
    0.06
     contributes
    0.06
     disappe
    0.06
     �
    0.06
     περισσότε
    0.06
    Activations Density 0.032%

    No Known Activations