© 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
    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. 30511
    Prev
    Next
    INDEX
    Explanations

    said

    np_max-act · gemini-2.0-flash

    This neuron spotlights reporting or attribution phrases—i.e. verbs and markers like “said,” “told,” “reported,” and similar speaker‐attribution cues.

    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
    assuming
    -0.07
    seniz
    -0.06
     与
    -0.06
     onDestroy
    -0.06
     अध
    -0.06
    äl
    -0.06
     hotel
    -0.06
     Ayrıca
    -0.06
    abis
    -0.06
    ng
    -0.06
    POSITIVE LOGITS
     répond
    0.07
     Ιω
    0.07
    _COMM
    0.06
    λό
    0.06
    (ticket
    0.06
     spoilers
    0.06
    .strategy
    0.06
    _terms
    0.06
    شنامه
    0.06
    .ssl
    0.06
    Activations Density 0.032%

    No Known Activations