© 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. 687
    Prev
    Next
    INDEX
    Explanations

    19XX years

    np_max-act · gemini-2.0-flash

    The neuron activates on numeric tokens corresponding to four‐digit year references (especially those in Olympic participation contexts).

    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
     infections
    -0.08
     bottle
    -0.07
    filt
    -0.07
    mscorlib
    -0.07
     controlled
    -0.07
    _correct
    -0.06
     fim
    -0.06
    /people
    -0.06
    err
    -0.06
    bilder
    -0.06
    POSITIVE LOGITS
    �
    0.06
     çıkar
    0.06
    URL
    0.06
    .spaceBetween
    0.06
     mát
    0.06
     Υπο
    0.05
    Quest
    0.05
    =document
    0.05
    [color
    0.05
    保护
    0.05
    Activations Density 0.002%

    No Known Activations