© 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
    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. 66102
    Prev
    Next
    INDEX
    Explanations

    code

    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
    PLIC
    -0.06
     Росії
    -0.06
    ABCDE
    -0.06
     подк
    -0.06
    彼
    -0.06
    ormap
    -0.06
    (`/
    -0.06
     <--
    -0.06
     některé
    -0.06
    ерк
    -0.05
    POSITIVE LOGITS
    xygen
    0.08
     Oxygen
    0.08
    税
    0.07
     EN
    0.07
     Updated
    0.07
     craving
    0.07
    positories
    0.06
     Expression
    0.06
    odyn
    0.06
    abyte
    0.06
    Activations Density 0.001%

    No Known Activations