© 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. 128624
    Prev
    Next
    INDEX
    Explanations

    manufacturing

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of a company’s manufacturing or product‐selling activities (e.g. “manufactures,” “sells,” “products,” “structures,” “manufacturers,” 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
    iy
    -0.07
    system
    -0.06
    urring
    -0.06
    _segment
    -0.06
    -suite
    -0.06
     torpedo
    -0.06
    Dict
    -0.06
    cancelled
    -0.06
     washed
    -0.06
    umbed
    -0.06
    POSITIVE LOGITS
     tới
    0.07
    ριά
    0.07
    intage
    0.06
     brute
    0.06
    lass
    0.06
    كية
    0.06
    ğinin
    0.06
     ensl
    0.06
    天堂
    0.06
    .Here
    0.06
    Activations Density 0.095%

    No Known Activations