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

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    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. 21785
    Prev
    Next
    INDEX
    Explanations

    Chemicals

    np_max-act · gemini-2.0-flash

    The neuron detects chemical terms related to methyl groups—i.e. words containing “methyl,” “methylating,” or “methylation.”

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8

    terms related to chemical processes, particularly catalysis and molecular transformations.

    oai_token-act-pair · gpt-4o-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
    .Transaction
    -0.07
    .Environment
    -0.07
    _jwt
    -0.06
    acimiento
    -0.06
    ρω
    -0.06
     brunette
    -0.06
    Anderson
    -0.06
    lfw
    -0.06
    _singleton
    -0.06
    oubtedly
    -0.06
    POSITIVE LOGITS
     صنع
    0.06
    .ge
    0.06
    CONNECT
    0.06
    _Version
    0.06
    XXXXXXXX
    0.06
     сна
    0.06
     HDMI
    0.06
    ตาม
    0.06
     Dev
    0.06
     مط
    0.06
    Activations Density 0.029%

    No Known Activations