© 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. 126697
    Prev
    Next
    INDEX
    Explanations

    002

    np_max-act · gemini-2.0-flash

    This neuron activates on numeric fragments in comment metadata—especially parts of timestamps and dates.

    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
    WritableDatabase
    -0.07
    ategic
    -0.07
    谁
    -0.06
     debug
    -0.06
     tyr
    -0.06
     mie
    -0.06
    				
↵
    -0.06
    _tv
    -0.06
     Cooperation
    -0.06
    _ENCOD
    -0.06
    POSITIVE LOGITS
     Seriously
    0.06
     клі
    0.06
     dạng
    0.06
     Richardson
    0.06
    acky
    0.06
     Thomas
    0.06
    installer
    0.06
     Pulse
    0.06
    -template
    0.06
     Deferred
    0.06
    Activations Density 0.001%

    No Known Activations