© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 13503
    Prev
    Next
    INDEX
    Explanations

    offers of help

    np_max-act · gemini-2.0-flash

    This neuron detects first-person volunteer/offering phrases—statements like “I’ll send…,” “I will help…,” or “I’ll address…” that offer assistance or action.

    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
     NASA
    -0.07
     усл
    -0.06
     lure
    -0.06
    ASF
    -0.06
     INC
    -0.06
     lotion
    -0.06
    Advertising
    -0.06
     podmín
    -0.06
    隆
    -0.06
     underwear
    -0.06
    POSITIVE LOGITS
    +xml
    0.06
    örü
    0.06
    .bel
    0.06
    .contentOffset
    0.06
     Sender
    0.06
    UTURE
    0.06
    *****
↵
    0.06
    _signals
    0.06
    よび
    0.06
    rink
    0.06
    Activations Density 0.034%

    No Known Activations