© 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. 7-RESID-POST-AA
    11. 46145
    Prev
    Next
    INDEX
    Explanations

    quotation marks

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    頻
    -0.06
    250
    -0.06
    eygamber
    -0.06
     Calgary
    -0.06
     assms
    -0.06
     speedy
    -0.06
    part
    -0.06
     maternity
    -0.06
     用
    -0.06
    ゞ
    -0.06
    POSITIVE LOGITS
     throw
    0.07
     OUTER
    0.06
    mdl
    0.06
    .onView
    0.06
     ($('#
    0.06
     cesty
    0.06
     Throw
    0.06
     tossed
    0.05
     scarce
    0.05
     проз
    0.05
    Activations Density 0.025%

    No Known Activations