© 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. 754
    Prev
    Next
    INDEX
    Explanations

    about

    np_max-act · gemini-2.0-flash

    stories featuring young male protagonists who experience growth or challenges during significant life events.

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

    This neuron detects the user’s request to “Tell me a story,” i.e. the word “story” (and its immediate context) in an instruction.

    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
    _deploy
    -0.06
    classes
    -0.06
     Elliott
    -0.06
    Text
    -0.06
     cared
    -0.06
     uploading
    -0.06
     obscured
    -0.06
    <Text
    -0.06
    .Contract
    -0.06
    illator
    -0.06
    POSITIVE LOGITS
    (Global
    0.08
    čů
    0.08
    AMB
    0.07
    .chdir
    0.06
     SOS
    0.06
     Lesb
    0.06
     infiltr
    0.06
     قانون
    0.06
     notifies
    0.06
    xfd
    0.06
    Activations Density 0.017%

    No Known Activations