© 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. 614
    Prev
    Next
    INDEX
    Explanations

    Formal/technical writing

    np_max-act · gemini-2.0-flash

    This neuron responds to formal abstract nouns common in technical or scientific writing (e.g. “structure,” “architecture,” “answer,” “predictions,” “attainment”).

    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
     cleanup
    -0.07
    !";↵
    -0.07
     Universal
    -0.07
    意味
    -0.06
    stream
    -0.06
     �
    -0.06
    Unless
    -0.06
    emaakt
    -0.06
    Confirm
    -0.06
    Keeping
    -0.06
    POSITIVE LOGITS
    )./
    0.07
     guardar
    0.06
    _partitions
    0.06
    ене
    0.06
    EMY
    0.06
    ‐-
    0.06
    _rnn
    0.06
     posY
    0.06
     Veter
    0.06
    _CLI
    0.06
    Activations Density 0.026%

    No Known Activations