© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 3-RESID-POST-AA
    11. 121191
    Prev
    Next
    INDEX
    Explanations

    protein

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     trending
    -0.07
     Debate
    -0.07
     correspondence
    -0.07
    fw
    -0.06
     pís
    -0.06
    _USE
    -0.06
     snapping
    -0.06
     س
    -0.06
     ecology
    -0.06
    hur
    -0.06
    POSITIVE LOGITS
     protein
    0.16
     Protein
    0.11
    tein
    0.07
    protein
    0.07
     nanop
    0.07
    Keith
    0.06
    lığını
    0.06
    Portable
    0.06
     eventually
    0.06
    verage
    0.06
    Activations Density 0.022%

    No Known Activations