© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52752
    Prev
    Next
    INDEX
    Explanations

    Length or dimension

    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
     června
    -0.06
    。しかし
    -0.06
    fullscreen
    -0.06
     Vimeo
    -0.06
    verify
    -0.06
    یا
    -0.06
    VIDEO
    -0.06
    azon
    -0.06
    src
    -0.06
    .."
    -0.06
    POSITIVE LOGITS
     korum
    0.06
     Istanbul
    0.06
     Adv
    0.06
     Turkey
    0.06
    .direct
    0.06
     Memory
    0.06
     QTest
    0.06
    ख
    0.06
    .ACT
    0.06
     how
    0.06
    Activations Density 0.020%

    No Known Activations