© 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. 110080
    Prev
    Next
    INDEX
    Explanations

    positive adjectives

    np_max-act · gemini-2.0-flash

    The neuron fires on promotional or hyperbolic adjectives and superlatives used to boast quality (e.g. “best,” “ultimate,” “luxurious,” “marvelous”).

    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
     needs
    -0.07
    مج
    -0.06
     삶
    -0.06
    حل
    -0.06
    _BACKEND
    -0.06
     захисту
    -0.06
    朋友
    -0.06
    ,args
    -0.06
     REQUIRED
    -0.06
     ثم
    -0.06
    POSITIVE LOGITS
    idi
    0.07
    /ec
    0.07
    navigate
    0.06
    .getLabel
    0.06
     volcanic
    0.06
     Cave
    0.06
    -filter
    0.06
    [test
    0.06
    _esc
    0.06
     comput
    0.06
    Activations Density 0.083%

    No Known Activations