© 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. 93823
    Prev
    Next
    INDEX
    Explanations

    .html

    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
    /cache
    -0.08
    -hash
    -0.07
     doubts
    -0.07
     jamais
    -0.07
    -aff
    -0.07
     scatter
    -0.07
    .AutoScaleMode
    -0.06
     Niagara
    -0.06
    (users
    -0.06
     Scatter
    -0.06
    POSITIVE LOGITS
    .html
    0.08
    %B
    0.07
     committee
    0.07
     Yugosl
    0.06
    urbed
    0.06
     후
    0.06
    ecal
    0.06
     Magento
    0.06
    Dur
    0.06
    odyn
    0.06
    Activations Density 0.002%

    No Known Activations