© 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. 42677
    Prev
    Next
    INDEX
    Explanations

    Descriptive, objective writing

    np_max-act · gemini-2.0-flash

    The neuron fires on adverbial modifiers and qualifying words (e.g. “somewhat,” “for effect,” “being,” “add-ons”) that add nuance or hedge a descriptive statement.

    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
    urr
    -0.08
    resp
    -0.07
    _vars
    -0.06
    BILE
    -0.06
     jade
    -0.06
     stair
    -0.06
     Bunu
    -0.06
    _tid
    -0.06
    .Call
    -0.06
     عبدال
    -0.06
    POSITIVE LOGITS
     nouve
    0.06
    mh
    0.06
     vrai
    0.06
    是一个
    0.06
     jon
    0.06
     ECB
    0.06
     hypotheses
    0.06
    ardash
    0.06
    ेच
    0.06
     balancing
    0.06
    Activations Density 0.121%

    No Known Activations