© 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 EvalsExportsinterp-engineNEWAPI 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. 94172
    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
    oping
    -0.07
    (camera
    -0.07
     VT
    -0.07
     peso
    -0.07
    .iterator
    -0.07
    Bookmark
    -0.06
    賢
    -0.06
    Beyond
    -0.06
     écrit
    -0.06
     FTP
    -0.06
    POSITIVE LOGITS
    _student
    0.07
     Kah
    0.06
    workers
    0.06
    訴
    0.06
    련
    0.06
    flammatory
    0.06
     mocked
    0.06
     sodium
    0.06
     profiler
    0.06
    ایج
    0.06
    Activations Density 0.004%

    No Known Activations