© 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. 45300
    Prev
    Next
    INDEX
    Explanations

    parenthesis and brackets

    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
    Negative Logits
    .Formatter
    -0.07
     цель
    -0.06
    pend
    -0.06
    Unsupported
    -0.06
     PyTuple
    -0.06
     adres
    -0.06
    (script
    -0.06
     captcha
    -0.06
    (sid
    -0.06
     multer
    -0.06
    POSITIVE LOGITS
     Levy
    0.07
    iral
    0.06
     waveform
    0.06
     BV
    0.06
    ова
    0.06
    43
    0.06
     molded
    0.06
     gamble
    0.06
    hydro
    0.06
    eor
    0.06
    Activations Density 0.007%

    No Known Activations