© 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. 124007
    Prev
    Next
    INDEX
    Explanations

    quality

    np_max-act · gemini-2.0-flash

    the neuron activates on evaluative adjectives and adverbial modifiers (like “quality,” “reliable,” “professional,” “high,” etc.) used to promote service excellence.

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    keywords related to plumbing services and maintenance.

    oai_token-act-pair · gpt-4o-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
    errMsg
    -0.06
    anneer
    -0.06
    utedString
    -0.06
    phins
    -0.06
     гре
    -0.06
    Depth
    -0.06
    ixe
    -0.06
    ()↵↵↵↵
    -0.06
     campus
    -0.06
     میکن
    -0.06
    POSITIVE LOGITS
    sob
    0.08
    ाहत
    0.07
    inou
    0.07
     मण
    0.07
     Malays
    0.06
     representative
    0.06
    нее
    0.06
    _same
    0.06
     حم
    0.06
    FUL
    0.06
    Activations Density 0.062%

    No Known Activations