© 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
    3. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    5. Llama3.1-8B-IT (Instruct)
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 44202
    Prev
    Next
    INDEX
    Explanations

    scientific abstracts

    np_max-act · gemini-2.0-flash

    This neuron responds to mentions of multi-point correlation functions (e.g. “four-point correlator”) in theoretical‐physics abstracts.

    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
    หนด
    -0.07
     $$
    -0.07
    thesized
    -0.07
    $$
    -0.07
     arbitrarily
    -0.07
     states
    -0.06
     observed
    -0.06
     зов
    -0.06
     depicted
    -0.06
     demanded
    -0.06
    POSITIVE LOGITS
    zza
    0.08
    gré
    0.07
    sko
    0.07
     ACE
    0.06
     رضا
    0.06
    YELLOW
    0.06
    -Col
    0.06
     qw
    0.06
     rám
    0.06
    거
    0.06
    Activations Density 0.055%

    No Known Activations