© 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
    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. 779
    Prev
    Next
    INDEX
    Explanations

    cellular

    np_max-act · gemini-2.0-flash

    The neuron detects mentions of biological organization scales or levels (e.g. “cellular,” “molecular,” “membrane,” “subcellular,” “nervous”).

    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
    _DT
    -0.07
     letto
    -0.06
     ART
    -0.06
    onnen
    -0.06
    loy
    -0.06
     Brent
    -0.06
    ास
    -0.06
     Blizzard
    -0.06
     amigos
    -0.06
     telling
    -0.06
    POSITIVE LOGITS
    coach
    0.07
    _bid
    0.07
    outine
    0.06
     recruit
    0.06
    charAt
    0.06
    Fcn
    0.06
    ‡
    0.06
     本
    0.06
     ин
    0.06
    مول
    0.06
    Activations Density 0.021%

    No Known Activations