© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 12462
    Prev
    Next
    INDEX
    Explanations

    scientific research

    np_max-act · gemini-2.0-flash

    technical terminology and concepts related to protein science and molecular biology.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    This neuron detects mentions of protein mutations or post‐translational modifications that underlie disease states.

    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
    awe
    -0.07
     venom
    -0.06
    mainwindow
    -0.06
    -co
    -0.06
    ](
    -0.06
    バイ
    -0.06
     cocaine
    -0.06
    FromDate
    -0.06
     fungi
    -0.06
     infusion
    -0.06
    POSITIVE LOGITS
    _drv
    0.07
    ्यकत
    0.06
     Arb
    0.06
    .El
    0.06
    _SUM
    0.06
    .Wh
    0.06
    rparr
    0.06
    (priv
    0.06
    抑
    0.06
    _FW
    0.06
    Activations Density 0.059%

    No Known Activations