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. 86204
    Prev
    Next
    INDEX
    Explanations

    any/of possibility/existence texts

    np_max-act · gemini-2.0-flash

    The neuron fires on indefinite quantifier expressions—especially “any” (often in “any of”) and related words like “anything.”

    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
    cg
    -0.07
    566
    -0.07
    、
    -0.06
    ็น
    -0.06
    iteration
    -0.06
    .dense
    -0.06
    刚
    -0.06
     egg
    -0.06
     Egg
    -0.06
    ainter
    -0.06
    POSITIVE LOGITS
     any
    0.08
     Any
    0.08
    .WRITE
    0.07
     oe
    0.07
    operand
    0.07
    อดภ
    0.06
     currentValue
    0.06
     anytime
    0.06
     anything
    0.06
    .getLast
    0.06
    Activations Density 0.045%

    No Known Activations