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. 51119
    Prev
    Next
    INDEX
    Explanations

    AM radio

    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
    ici
    -0.07
    南
    -0.06
    [MAXN
    -0.06
    вещ
    -0.06
    куль
    -0.06
    idelity
    -0.06
    ΟΙ
    -0.06
    -material
    -0.06
     panels
    -0.06
    UIImageView
    -0.06
    POSITIVE LOGITS
    ificaciones
    0.07
     Without
    0.06
    τωση
    0.06
    AppState
    0.06
    Web
    0.06
     فس
    0.06
     unwitting
    0.06
     あ
    0.06
    لاق
    0.06
    …)↵↵
    0.06
    Activations Density 0.039%

    No Known Activations