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. 100935
    Prev
    Next
    INDEX
    Explanations

    data structures

    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
     Kre
    -0.06
    (d
    -0.06
    '])
    ↵
    -0.06
     Mot
    -0.06
    .Update
    -0.06
    403
    -0.06
    -makers
    -0.06
     abandoned
    -0.06
    ruba
    -0.06
    -step
    -0.06
    POSITIVE LOGITS
     знаход
    0.07
     peg
    0.07
     phê
    0.07
    Chunk
    0.06
     bevor
    0.06
     шкі
    0.06
    ếp
    0.06
     thôi
    0.06
     باعث
    0.06
     كنت
    0.06
    Activations Density 0.025%

    No Known Activations