© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 105356
    Prev
    Next
    INDEX
    Explanations

    ,

    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
     contr
    -0.07
    fold
    -0.07
    ΕΙΣ
    -0.06
    像
    -0.06
    480
    -0.06
    ováním
    -0.06
    λον
    -0.06
     ekonom
    -0.06
    े,
    -0.06
    CHED
    -0.06
    POSITIVE LOGITS
    915
    0.06
     authService
    0.06
     enzymes
    0.06
     Ziel
    0.06
    _social
    0.06
    (always
    0.06
     NSMutable
    0.06
    strom
    0.06
    LoginForm
    0.06
    .Thread
    0.06
    Activations Density 0.002%

    No Known Activations