© 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. 6542
    Prev
    Next
    INDEX
    Explanations

    DC

    np_max-act · gemini-2.0-flash

    The neuron activates on the “USDC” case‐number tokens (the district‐court docket identifiers rendered with decimal values).

    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
     bay
    -0.07
     Hole
    -0.07
    _NEW
    -0.06
     cluster
    -0.06
    =[↵
    -0.06
    ivalent
    -0.06
    ↵        ↵        ↵
    -0.06
     hole
    -0.06
     Phys
    -0.06
    .biz
    -0.06
    POSITIVE LOGITS
    Sac
    0.07
     ΕΛ
    0.06
     verb
    0.06
     воздейств
    0.06
     BlueprintReadOnly
    0.06
     orbit
    0.06
    lex
    0.06
     đưa
    0.06
    enne
    0.06
     readFile
    0.05
    Activations Density 0.000%

    No Known Activations