© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 57243
    Prev
    Next
    INDEX
    Explanations

    storytelling

    np_max-act · gemini-2.0-flash

    instructions or guidelines related to narrative structure and storytelling processes.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron fires on words that name or describe elements of narrative‐writing advice—terms like “plot,” “characters,” “outline,” “story,” and other structural steps in a writing guide.

    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
    anto
    -0.07
     капіт
    -0.07
    .bz
    -0.06
     Jasper
    -0.06
    .getSize
    -0.06
     belki
    -0.06
    트
    -0.06
     partly
    -0.06
     Fn
    -0.06
    .Engine
    -0.06
    POSITIVE LOGITS
    릉
    0.08
    ':'
    0.07
    ố
    0.07
    ','
    0.07
     harmed
    0.06
    岁
    0.06
    fet
    0.06
    local
    0.06
     bát
    0.06
    ин
    0.06
    Activations Density 0.023%

    No Known Activations