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. 19220
    Prev
    Next
    INDEX
    Explanations

    case

    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
    ход
    -0.07
    Tier
    -0.06
     desarroll
    -0.06
     axiom
    -0.06
     RT
    -0.06
    ерти
    -0.06
     Chunk
    -0.06
     EA
    -0.06
     MagicMock
    -0.06
    innamon
    -0.06
    POSITIVE LOGITS
     cases
    0.09
     Presents
    0.08
     case
    0.08
    ,如
    0.07
     Case
    0.07
    ++;
    ↵
    0.07
     represents
    0.07
     statewide
    0.06
     representa
    0.06
     個
    0.06
    Activations Density 0.014%

    No Known Activations