© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 109288
    Prev
    Next
    INDEX
    Explanations

    was

    np_max-act · gemini-2.0-flash

    This neuron detects parenthesized biographical date ranges (birth/death years or full birth–death dates) following a person’s 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
    ★
    -0.08
    074
    -0.07
     Istanbul
    -0.07
    +'"
    -0.06
     endanger
    -0.06
    请求
    -0.06
    ;:;:
    -0.06
    <P
    -0.06
     bib
    -0.06
    =============
    -0.06
    POSITIVE LOGITS
    .scrollView
    0.07
    .rating
    0.07
    pick
    0.07
    .wallet
    0.06
    UDENT
    0.06
     suk
    0.06
     salvar
    0.06
    _entropy
    0.06
     Spatial
    0.06
     Wet
    0.06
    Activations Density 0.007%

    No Known Activations