© 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
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 54063
    Prev
    Next
    INDEX
    Explanations

    Chemical formulas

    np_max-act · gemini-2.0-flash

    This neuron detects mentions of specific chemical compounds or reagents in the text.

    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
    atemala
    -0.06
     cake
    -0.06
    あげ
    -0.06
    小时
    -0.06
     Cake
    -0.06
     DG
    -0.06
     riêng
    -0.06
    _index
    -0.06
     zurück
    -0.06
     erased
    -0.06
    POSITIVE LOGITS
    comma
    0.07
    .dump
    0.06
     hely
    0.06
    works
    0.06
    تيار
    0.06
    _cos
    0.06
    "}↵
    0.06
    olucion
    0.06
     mainly
    0.05
     cruising
    0.05
    Activations Density 0.044%

    No Known Activations