© 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. 109243
    Prev
    Next
    INDEX
    Explanations

    writing

    np_max-act · gemini-2.0-flash

    This neuron detects occurrences of the word “writing” (as in “I am writing…”) in formal email text.

    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
    느
    -0.06
    овор
    -0.06
    ToList
    -0.06
    itta
    -0.06
     áo
    -0.06
     frustr
    -0.06
    Calendar
    -0.06
     sudah
    -0.06
     škol
    -0.06
    alty
    -0.06
    POSITIVE LOGITS
    rita
    0.07
    ynamo
    0.07
    ‌ن
    0.07
    *dx
    0.07
    .GetOrdinal
    0.07
    rchive
    0.07
    IDO
    0.07
     Seconds
    0.07
     emitting
    0.07
    _readable
    0.07
    Activations Density 0.007%

    No Known Activations