© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 76479
    Prev
    Next
    INDEX
    Explanations

    Physics, Weyl semimetals

    np_max-act · gemini-2.0-flash

    terms related to the structural properties and phenomena of materials in solid-state physics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8
    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
    electric
    -0.07
     unforgettable
    -0.07
     groups
    -0.07
    beck
    -0.06
     sod
    -0.06
    -part
    -0.06
     ministries
    -0.06
    물
    -0.06
    Borders
    -0.06
     millennium
    -0.06
    POSITIVE LOGITS
    (Time
    0.06
     vaccination
    0.06
     invokevirtual
    0.06
    」を
    0.06
    :numel
    0.06
     duel
    0.06
     adalah
    0.06
     WALL
    0.06
    (abs
    0.06
     RAW
    0.06
    Activations Density 0.002%

    No Known Activations