Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    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. 15-RESID-POST-AA
    6. 10022
    Prev
    Next
    INDEX
    Explanations

    CSS

    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_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     thresholds
    -0.08
     mirrors
    -0.07
     bounty
    -0.07
    .cal
    -0.06
     проблем
    -0.06
    "For
    -0.06
     daß
    -0.06
     dispens
    -0.06
     prism
    -0.06
     müdür
    -0.06
    POSITIVE LOGITS
    SignIn
    0.06
    /connection
    0.06
    scheduled
    0.06
    Messenger
    0.06
     %↵↵
    0.06
    authorize
    0.06
    (bot
    0.06
    loom
    0.06
     userdata
    0.06
    �
    0.05
    Activations Density 0.000%

    No Known Activations