© 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. 89886
    Prev
    Next
    INDEX
    Explanations

    day

    np_max-act · gemini-2.0-flash

    This neuron consistently responds to occurrences of “everyday” (or “Every day”) in headings or introductory phrases.

    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
     leaks
    -0.07
     quest
    -0.07
     Kahn
    -0.07
     jul
    -0.06
     pul
    -0.06
     neh
    -0.06
     clique
    -0.06
     Bubble
    -0.06
     single
    -0.06
     laughter
    -0.06
    POSITIVE LOGITS
     everyday
    0.13
     Everyday
    0.11
    _drag
    0.08
    ethnic
    0.07
    Exercise
    0.07
    ümüz
    0.07
    easy
    0.07
     सज
    0.06
    -toast
    0.06
     Implemented
    0.06
    Activations Density 0.004%

    No Known Activations