© 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. 7-RESID-POST-AA
    11. 112836
    Prev
    Next
    INDEX
    Explanations

    -

    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
    olvable
    -0.07
    .TO
    -0.06
    лася
    -0.06
    HEST
    -0.06
    .beginPath
    -0.06
     lesen
    -0.06
    .rx
    -0.06
    τα
    -0.06
    .codec
    -0.06
    หนอง
    -0.06
    POSITIVE LOGITS
    inter
    0.07
     ++)
    0.07
     исп
    0.06
     revamped
    0.06
     complying
    0.06
    communications
    0.06
     convey
    0.06
    (filter
    0.06
    phoon
    0.06
     $?
    0.06
    Activations Density 0.003%

    No Known Activations