© 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. 125184
    Prev
    Next
    INDEX
    Explanations

    food

    np_max-act · gemini-2.0-flash

    The neuron activates on mentions of “food” (especially in “food service” contexts).

    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
    machine
    -0.07
     Goal
    -0.07
    Maker
    -0.07
    ить
    -0.07
    	size
    -0.07
    imators
    -0.07
    /~
    -0.07
    .Par
    -0.07
     목록
    -0.06
    omal
    -0.06
    POSITIVE LOGITS
     Gly
    0.06
     ایجاد
    0.06
     miscon
    0.06
    _kv
    0.06
     hid
    0.06
     distinguished
    0.06
     critically
    0.06
    ปลอดภ
    0.06
    .Microsoft
    0.06
    キング
    0.06
    Activations Density 0.006%

    No Known Activations