© 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. 116050
    Prev
    Next
    INDEX
    Explanations

    pear

    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
     Jub
    -0.07
     invo
    -0.07
    _runner
    -0.06
     arbit
    -0.06
     theorem
    -0.06
     kter
    -0.06
     NJ
    -0.06
     udrž
    -0.06
     αντι
    -0.06
    ＿_
    -0.06
    POSITIVE LOGITS
     Pearson
    0.15
    Pear
    0.13
     pear
    0.12
     Pear
    0.11
     Pearce
    0.09
     Pearl
    0.09
    pear
    0.09
    PEAR
    0.08
     sharper
    0.08
     Sears
    0.07
    Activations Density 0.003%

    No Known Activations