© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 41628
    Prev
    Next
    INDEX
    Explanations

    Positive sentiment

    np_max-act · gemini-2.0-flash

    The neuron fires on common polite-assistant phrasings—short, formulaic offers of help or affirmations (e.g. “Of course, I’d be happy to help,” “That sounds good to me,” “Alright, that makes sense,” etc.).

    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
    -cont
    -0.07
     ilişkin
    -0.07
    집
    -0.06
     reconstruct
    -0.06
     Kare
    -0.06
     including
    -0.06
    .food
    -0.06
     bright
    -0.06
     imitation
    -0.06
    -so
    -0.06
    POSITIVE LOGITS
    ?}",
    0.07
    :@"%@",
    0.07
    ancial
    0.07
    :"",
    0.06
    παίδ
    0.06
    irler
    0.06
    edes
    0.06
     Deutsch
    0.06
    ostel
    0.06
    equiv
    0.06
    Activations Density 0.043%

    No Known Activations