© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 44523
    Prev
    Next
    INDEX
    Explanations

    ?

    np_max-act · gemini-2.0-flash

    information related to personal details and preferences of individuals.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects special control tokens (e.g. end‐of‐text markers and header boundary tokens) that mark message or turn boundaries.

    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
    "))
    ↵
    -0.06
    JsonValue
    -0.06
     paramName
    -0.06
    "B
    -0.06
     яку
    -0.06
    δυ
    -0.06
    ')}↵
    -0.06
    expense
    -0.06
     지난
    -0.06
     попада
    -0.06
    POSITIVE LOGITS
    asel
    0.07
     Bulgarian
    0.07
    _episodes
    0.07
     Aleppo
    0.06
     очи
    0.06
    omens
    0.06
     Cellular
    0.06
    ardy
    0.06
    貸
    0.06
    798
    0.06
    Activations Density 0.066%

    No Known Activations