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

    Neuronpedia

    APIAssistant AxisNEWCircuit 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. 84413
    Prev
    Next
    INDEX
    Explanations

    chemical compounds

    np_max-act · gemini-2.0-flash

    The neuron fires on parts of systematic chemical names (IUPAC-style nomenclature) 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
    _hint
    -0.07
    Internal
    -0.07
     Tech
    -0.06
     Certificate
    -0.06
    Pixels
    -0.06
    ागत
    -0.06
     快
    -0.06
    	entry
    -0.06
     Hast
    -0.06
     Arts
    -0.06
    POSITIVE LOGITS
     zajímav
    0.06
     yandan
    0.06
    .hover
    0.06
    apphire
    0.06
    (today
    0.06
     vždy
    0.06
    .localizedDescription
    0.06
    updated
    0.06
    .Resize
    0.06
     参考
    0.06
    Activations Density 0.045%

    No Known Activations