© 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. 44401
    Prev
    Next
    INDEX
    Explanations

    deep

    np_max-act · gemini-2.0-flash

    The neuron activates on occurrences of “deep,” “neural,” “learning,” and related terms—i.e. it detects mentions of deep‐learning or neural‐network concepts.

    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
     intr
    -0.07
    ống
    -0.06
     tying
    -0.06
     собой
    -0.06
     spirited
    -0.06
     snork
    -0.06
     borrow
    -0.06
     Wig
    -0.06
     Ekon
    -0.06
    маз
    -0.06
    POSITIVE LOGITS
    ıp
    0.07
     Feast
    0.07
     (%)
    0.07
    (public
    0.07
     intersects
    0.06
    (convert
    0.06
     Ride
    0.06
     delivers
    0.06
    ;$
    0.06
    .getDate
    0.06
    Activations Density 0.004%

    No Known Activations