© 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. 126749
    Prev
    Next
    INDEX
    Explanations

    want

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of the verb “want” (and nearby “to”)—i.e. expressions of desire or intent.

    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
    因
    -0.06
     toddlers
    -0.06
     Carn
    -0.06
    semicolon
    -0.06
    _nd
    -0.06
    _sid
    -0.06
    Id
    -0.06
     provoke
    -0.06
    —from
    -0.06
     contributes
    -0.06
    POSITIVE LOGITS
     interested
    0.07
    atitude
    0.06
    izzly
    0.06
     keen
    0.06
    oslav
    0.06
     متف
    0.06
     prince
    0.06
    .white
    0.06
    llib
    0.06
    ORMAT
    0.06
    Activations Density 0.020%

    No Known Activations