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. 15-RESID-POST-AA
    6. 24575
    Prev
    Next
    INDEX
    Explanations

    accident, ident

    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
    labs
    -0.07
     Champagne
    -0.07
     beers
    -0.07
     emergence
    -0.07
    urities
    -0.06
    ля
    -0.06
     THEORY
    -0.06
     featured
    -0.06
    cloak
    -0.06
     formation
    -0.06
    POSITIVE LOGITS
     accident
    0.11
     accidents
    0.09
     Accident
    0.08
    らず
    0.06
    っく
    0.06
    čí
    0.06
    事故
    0.06
    _INT
    0.06
    нием
    0.06
     verdict
    0.06
    Activations Density 0.029%

    No Known Activations