© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 13638
    Prev
    Next
    INDEX
    Explanations

    technology and internet

    np_max-act · gemini-2.0-flash

    This neuron spots specific named entities and technical proper nouns (e.g., brand/model names, chemical/drug names, and other capitalized terms).

    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
    BALL
    -0.07
    (msg
    -0.07
    џЭ
    -0.06
    949
    -0.06
    "To
    -0.06
    hra
    -0.06
    meldung
    -0.06
     IX
    -0.06
    (pin
    -0.06
    „To
    -0.06
    POSITIVE LOGITS
     Exhibit
    0.07
    ový
    0.07
     francaise
    0.06
    己
    0.06
    _storage
    0.06
    owej
    0.06
    logged
    0.06
     peng
    0.06
     Inter
    0.06
    ской
    0.06
    Activations Density 0.474%

    No Known Activations