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. 19-RESID-POST-AA
    6. 9875
    Prev
    Next
    INDEX
    Explanations

    uring

    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
     arrogant
    -0.07
     tand
    -0.06
     aup
    -0.06
    (Conv
    -0.06
    Bas
    -0.06
     robes
    -0.06
    Subsystem
    -0.06
     Frau
    -0.06
    (vp
    -0.06
     fleeting
    -0.06
    POSITIVE LOGITS
    kan
    0.07
    ToJson
    0.07
    ayout
    0.07
    .choice
    0.07
    σεις
    0.07
    issance
    0.06
    Configure
    0.06
    .constants
    0.06
    قام
    0.06
    setScale
    0.06
    Activations Density 0.310%

    No Known Activations