© 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. 15-RESID-POST-AA
    11. 37633
    Prev
    Next
    INDEX
    Explanations

    Storing at a temperature

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     selects
    -0.07
    िस
    -0.07
    ERTICAL
    -0.06
    StartTime
    -0.06
    iones
    -0.06
     зда
    -0.06
     sulf
    -0.06
    ROKE
    -0.06
     ben
    -0.06
    士
    -0.06
    POSITIVE LOGITS
    _ty
    0.06
     http
    0.06
     }↵↵
    0.06
     spared
    0.06
     Reno
    0.06
    ${
    0.06
     https
    0.06
    .hwp
    0.06
     pracy
    0.06
    =output
    0.06
    Activations Density 0.010%

    No Known Activations