Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 51036
    Prev
    Next
    INDEX
    Explanations

    с

    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
    buffers
    -0.08
    “These
    -0.07
     hands
    -0.07
    ущ
    -0.07
     uniqu
    -0.07
     anything
    -0.07
    looking
    -0.06
    "These
    -0.06
    thr
    -0.06
     nog
    -0.06
    POSITIVE LOGITS
     с
    0.08
    icip
    0.07
     Перед
    0.07
    RelativeTo
    0.07
    řich
    0.07
     À
    0.06
    ครอบ
    0.06
     груз
    0.06
     هنگام
    0.06
     isIn
    0.06
    Activations Density 0.091%

    No Known Activations