© 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. 42547
    Prev
    Next
    INDEX
    Explanations

    fan fiction stories

    np_max-act · gemini-2.0-flash

    The neuron is triggered by terms and placeholders associated with fan‐fiction prompts—words like “fanfic,” “fic,” “book,” “series,” and “NAME_#.”

    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
     Grow
    -0.07
    umbles
    -0.06
    /view
    -0.06
     발매
    -0.06
    氣
    -0.06
     reliability
    -0.06
    seed
    -0.06
    ixin
    -0.06
     آموز
    -0.06
    [code
    -0.06
    POSITIVE LOGITS
    (Unknown
    0.06
    .AutoComplete
    0.06
     sacrific
    0.06
     burgl
    0.06
     Therefore
    0.06
     συ
    0.06
    lesc
    0.05
    -too
    0.05
    нах
    0.05
    lovak
    0.05
    Activations Density 0.060%

    No Known Activations