© 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. 67750
    Prev
    Next
    INDEX
    Explanations

    Physics problems

    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
     Jar
    -0.07
    istros
    -0.06
    ，“
    -0.06
     Ital
    -0.06
    bsites
    -0.06
     elgg
    -0.06
     McG
    -0.06
     Difference
    -0.06
    翰
    -0.06
    ..."
    -0.06
    POSITIVE LOGITS
    /ch
    0.06
    持ち
    0.06
     nuanced
    0.06
    /pol
    0.06
    .Mobile
    0.06
    <|begin_of_text|>
    0.06
    -priced
    0.06
     ResourceType
    0.06
    ERVED
    0.06
    inee
    0.06
    Activations Density 0.021%

    No Known Activations