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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 104986
    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     हज
    -0.07
    .bad
    -0.07
     Haven
    -0.07
    What
    -0.06
     Surv
    -0.06
     analyzed
    -0.06
    ohn
    -0.06
     Healthy
    -0.06
     burden
    -0.06
     HOW
    -0.06
    POSITIVE LOGITS
     ::
    0.11
     :::
    0.08
     ->
    0.08
     Retro
    0.07
    ////////////////////////////////////////////////////////////////////////////////////////////////
    0.07
    공
    0.07
    空
    0.07
     QtCore
    0.07
     scripted
    0.07
    .subplots
    0.07
    Activations Density 0.004%

    No Known Activations