© 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. 89737
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash

    The neuron activates on references to science‐fiction or other fictional contexts and terms (e.g. mentions of Star Trek, telekinesis in fiction, etc.).

    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
    leet
    -0.07
     같이
    -0.07
     wallet
    -0.06
    ,result
    -0.06
     unlawful
    -0.06
    _source
    -0.06
    associated
    -0.06
    ंट
    -0.06
     borrowed
    -0.06
    ρυ
    -0.06
    POSITIVE LOGITS
     ним
    0.06
    ×</
    0.06
    .pid
    0.06
    _PARTITION
    0.06
    /__
    0.06
    (parseInt
    0.06
    aticon
    0.06
    장을
    0.06
     говорить
    0.06
    "><!--
    0.06
    Activations Density 0.214%

    No Known Activations