© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 23-RESID-POST-AA
    11. 68181
    Prev
    Next
    INDEX
    Explanations

    within

    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
     identity
    -0.07
    lom
    -0.06
     EDUC
    -0.06
    .idea
    -0.06
     terms
    -0.06
    /Documents
    -0.06
     potato
    -0.06
    .bn
    -0.06
     Agricultural
    -0.06
    .hs
    -0.06
    POSITIVE LOGITS
     ----------------
    0.07
    rière
    0.07
     performan
    0.07
     ostat
    0.06
     blí
    0.06
    (parsed
    0.06
     
    0.06
     个
    0.06
    щё
    0.06
    違い
    0.06
    Activations Density 0.103%

    No Known Activations