© 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. 73653
    Prev
    Next
    INDEX
    Explanations

    quotations

    np_max-act · gemini-2.0-flash

    The neuron fires on concise two-word formal noun phrases made up of a qualifying adjective/gerund plus a noun (e.g. “absolute majority,” “systematic violations,” “tabling the motion”).

    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
    .Middle
    -0.07
    Volt
    -0.06
    át
    -0.06
    เธ
    -0.06
    _FLUSH
    -0.06
    lacağı
    -0.06
    Jac
    -0.06
    زب
    -0.06
     Dispatch
    -0.06
    PerPixel
    -0.06
    POSITIVE LOGITS
     sayı
    0.07
    .flink
    0.07
     남
    0.07
    ้าพ
    0.07
     deserted
    0.06
    략
    0.06
     contraction
    0.06
     Inform
    0.06
    urry
    0.06
    语言
    0.06
    Activations Density 0.033%

    No Known Activations