© 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. 90954
    Prev
    Next
    INDEX
    Explanations

    Informal conversational text

    np_max-act · gemini-2.0-flash

    The neuron spotlights temporal clauses that reference a past point in time—e.g. phrases like “back in April.”

    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
     �
    -0.06
     administrators
    -0.06
     siege
    -0.06
    üven
    -0.06
    ium
    -0.06
     Searches
    -0.06
     Králové
    -0.06
     defenders
    -0.06
    оу
    -0.06
    _definitions
    -0.06
    POSITIVE LOGITS
    <HashMap
    0.08
    :url
    0.07
    แปลง
    0.07
    gün
    0.06
    licenses
    0.06
    press
    0.06
     関連
    0.06
    regn
    0.06
     Tarihi
    0.06
     하
    0.06
    Activations Density 0.091%

    No Known Activations