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. 7-RESID-POST-AA
    6. 4069
    Prev
    Next
    INDEX
    Explanations

    пред

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    бас
    -0.07
     活
    -0.07
     Osw
    -0.07
     گاه
    -0.06
     Howe
    -0.06
     Hughes
    -0.06
    ヌ
    -0.06
    έρα
    -0.06
    .OS
    -0.06
    ASSWORD
    -0.06
    POSITIVE LOGITS
     пред
    0.19
     Пред
    0.12
    ред
    0.08
     против
    0.07
     предус
    0.07
    levelname
    0.07
    сяг
    0.07
    pek
    0.07
    equals
    0.07
    .related
    0.07
    Activations Density 0.003%

    No Known Activations