© 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
    4. Resid Post - 131k
    5. 19-RESID-POST-AA
    6. 28113
    Prev
    Next
    INDEX
    Explanations

    page

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     beet
    -0.07
     getString
    -0.06
     chemicals
    -0.06
    Relationship
    -0.06
     빛
    -0.06
     debts
    -0.06
     jestli
    -0.06
     сторону
    -0.06
     Notification
    -0.06
    思い
    -0.06
    POSITIVE LOGITS
    ERSION
    0.07
    PS
    0.07
    _NODES
    0.07
     PS
    0.07
    .base
    0.07
     PE
    0.07
    Ace
    0.06
    adaş
    0.06
     디
    0.06
     TTC
    0.06
    Activations Density 0.010%

    No Known Activations