© 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 (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 72752
    Prev
    Next
    INDEX
    Explanations

    Legal/court declarations and injunctions

    np_max-act · gemini-2.0-flash

    legal terminology related to civil rights and court proceedings.

    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
    >F
    -0.07
     Frog
    -0.07
     bites
    -0.07
    No
    -0.06
    itoris
    -0.06
     ČR
    -0.06
    ürk
    -0.06
    _sidebar
    -0.06
    urd
    -0.06
    ivot
    -0.06
    POSITIVE LOGITS
    _email
    0.06
     emphasis
    0.06
    лан
    0.06
    .object
    0.06
    ира
    0.06
     jsonify
    0.06
    」（
    0.06
     Runnable
    0.06
     가져
    0.06
    '></
    0.06
    Activations Density 0.001%

    No Known Activations