Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    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. 126438
    Prev
    Next
    INDEX
    Explanations

    DNA/RNA

    np_max-act · gemini-2.0-flash

    The neuron responds to occurrences of “nucleic acid,” especially in the context of “deoxyribonucleic acid” (DNA) or “ribonucleic acid” (RNA).

    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
    ̀
    -0.07
    595
    -0.07
     şart
    -0.07
     tighter
    -0.06
     Socialist
    -0.06
    MSG
    -0.06
    imulation
    -0.06
    ời
    -0.06
    .substring
    -0.06
    qx
    -0.06
    POSITIVE LOGITS
     Carn
    0.06
     있어
    0.06
    사지
    0.06
    ingular
    0.06
    기는
    0.06
    าป
    0.06
    ząd
    0.06
    ;">
    ↵
    0.06
     bowling
    0.06
    |--------------------------------------------------------------------------↵
    0.06
    Activations Density 0.002%

    No Known Activations