© 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. 13578
    Prev
    Next
    INDEX
    Explanations

    programming discussions

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of other users, i.e. “@”-prefixed usernames.

    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
     рівень
    -0.08
    .:.:.:.:.:.:.:.:.:.:.:.:.:.:.:.:
    -0.06
    кою
    -0.06
    *v
    -0.06
    _FIRST
    -0.06
    _refl
    -0.06
     před
    -0.06
     Ya
    -0.06
     ceil
    -0.06
     생활
    -0.06
    POSITIVE LOGITS
    bage
    0.06
     chopped
    0.06
    ometer
    0.06
     пал
    0.06
    lias
    0.06
     Lottery
    0.06
     Casinos
    0.06
    orarily
    0.06
     Sergeant
    0.06
     dati
    0.06
    Activations Density 0.004%

    No Known Activations