© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 18468
    Prev
    Next
    INDEX
    Explanations

    Glaucoma

    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
    _additional
    -0.07
     Oven
    -0.06
    trasound
    -0.06
     Including
    -0.06
    _objs
    -0.06
    _depart
    -0.06
     Abyss
    -0.06
     ב
    -0.06
    Report
    -0.06
    _SECOND
    -0.06
    POSITIVE LOGITS
    idak
    0.08
    уск
    0.08
    ửi
    0.07
    polate
    0.07
    341
    0.07
    aze
    0.07
    izik
    0.06
     continues
    0.06
     *[
    0.06
    unuz
    0.06
    Activations Density 0.001%

    No Known Activations