© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW 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. 36389
    Prev
    Next
    INDEX
    Explanations

    amplify

    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
    Forecast
    -0.07
     erotic
    -0.07
    lossen
    -0.07
    .gen
    -0.07
    _sub
    -0.07
    >${
    -0.07
    cene
    -0.07
     menace
    -0.06
     任
    -0.06
     underway
    -0.06
    POSITIVE LOGITS
     amplified
    0.12
     amplify
    0.11
     ampl
    0.10
    Miller
    0.08
     Ampl
    0.08
    -url
    0.07
     dil
    0.06
     gracefully
    0.06
     amplifier
    0.06
     disproportionately
    0.06
    Activations Density 0.003%

    No Known Activations