© 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. 68891
    Prev
    Next
    INDEX
    Explanations

    making or canceling plans

    np_max-act · gemini-2.0-flash

    The neuron detects tokens involved in making social plans or invitations (e.g. suggesting “go to the movies this weekend” or “making plans”).

    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
    Kit
    -0.06
     gia
    -0.06
    .mean
    -0.06
    Forum
    -0.06
    fwrite
    -0.06
     significa
    -0.06
     과정
    -0.06
     Jam
    -0.06
     recognizer
    -0.06
    -hand
    -0.06
    POSITIVE LOGITS
    uae
    0.07
    _MEM
    0.06
    :black
    0.06
    asjon
    0.06
     interfering
    0.06
     deadlock
    0.06
     schl
    0.06
    ackle
    0.06
    .IsNullOr
    0.06
    Activ
    0.06
    Activations Density 0.059%

    No Known Activations