© 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. 7954
    Prev
    Next
    INDEX
    Explanations

    public speaking

    np_max-act · gemini-2.0-flash

    specific personal experiences and vulnerabilities related to social anxiety.

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

    The neuron activates on tokens referring to public speaking or giving speeches (e.g. “public,” “speaking,” “speech,” “presentation”).

    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
    /Product
    -0.07
    leitung
    -0.07
    Capacity
    -0.07
     harbor
    -0.07
    	option
    -0.07
    .Currency
    -0.07
    National
    -0.06
     pistols
    -0.06
    最終
    -0.06
    _station
    -0.06
    POSITIVE LOGITS
    ↵     ↵
    0.06
    errals
    0.06
    ripple
    0.06
     onstage
    0.06
     Nude
    0.06
    <Person
    0.06
    ǐ
    0.06
    arnings
    0.06
    .Sound
    0.06
    getJSON
    0.06
    Activations Density 0.006%

    No Known Activations