© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 12537
    Prev
    Next
    INDEX
    Explanations

    constructive feedback

    np_max-act · gemini-2.0-flash

    The neuron fires on words and phrases that propose giving help or guidance—especially “suggestions,” “feedback,” “provide,” and similar offers of assistance.

    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
     appending
    -0.06
    amb
    -0.06
    _PRO
    -0.06
    Token
    -0.06
    Susp
    -0.06
     lamp
    -0.06
    Runs
    -0.06
    ONES
    -0.06
     punk
    -0.06
    hud
    -0.05
    POSITIVE LOGITS
     góp
    0.08
     přij
    0.07
    prs
    0.07
     weiß
    0.07
     vX
    0.07
     Gr
    0.07
     alan
    0.07
     SMTP
    0.06
    _alive
    0.06
    toArray
    0.06
    Activations Density 0.056%

    No Known Activations