© 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. 85742
    Prev
    Next
    INDEX
    Explanations

    adjectives

    np_max-act · gemini-2.0-flash

    The neuron activates on positive, descriptive adjectives that praise or highlight appeal (e.g. dazzling, gorgeous, lustrous, fun, flirty).

    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
    fic
    -0.07
    ihu
    -0.06
    -sm
    -0.06
    OnClickListener
    -0.06
     dosud
    -0.06
     legally
    -0.06
    鑑
    -0.06
    џџџџ
    -0.06
    더
    -0.06
    상을
    -0.06
    POSITIVE LOGITS
    }")↵
    0.07
    (Channel
    0.07
    attrs
    0.06
    shall
    0.06
     göç
    0.06
     Knowledge
    0.06
     Mansion
    0.06
     Rah
    0.06
     Stone
    0.06
     Appe
    0.06
    Activations Density 0.094%

    No Known Activations