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

    Neuronpedia

    Jacobian LensNEW
    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. 114882
    Prev
    Next
    INDEX
    Explanations

    synthesize

    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
    (sockfd
    -0.06
    銀行
    -0.06
    /from
    -0.06
    안내
    -0.06
    .Head
    -0.06
    IsRequired
    -0.06
     sorting
    -0.06
    .Android
    -0.06
    urtles
    -0.06
    (_('
    -0.06
    POSITIVE LOGITS
    synthesize
    0.12
     Conj
    0.06
    催
    0.06
    -comments
    0.06
    avadoc
    0.06
    setq
    0.06
    pic
    0.06
    زل
    0.06
     Haw
    0.06
     Governors
    0.06
    Activations Density 0.001%

    No Known Activations