Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & 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. 11-RESID-POST-AA
    6. 40533
    Prev
    Next
    INDEX
    Explanations

    )(

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of procedural rule citations—especially “Rule 12(b)(6)” and its parenthesized numeric parts.

    oai_token-act-pair · o4-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
    дают
    -0.07
    Pred
    -0.07
    _sessions
    -0.06
    Educ
    -0.06
     jde
    -0.06
     Gareth
    -0.06
    анный
    -0.06
     overhaul
    -0.06
    .tmp
    -0.06
    μέν
    -0.06
    POSITIVE LOGITS
     <!
    0.07
     energy
    0.07
    .geometry
    0.06
     О
    0.06
    >Main
    0.06
     HAS
    0.06
     connecting
    0.06
    bris
    0.06
     Energy
    0.06
    ensity
    0.06
    Activations Density 0.001%

    No Known Activations