© 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
    7. Resid Post - 131k
    9. 11-RESID-POST-AA
    11. 29952
    Prev
    Next
    INDEX
    Explanations

    Insufficient funds, bounced checks

    np_max-act · gemini-2.0-flash

    The neuron detects references to checks being dishonored or bounced (insufficient-funds payments).

    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
    保存
    -0.07
     certifications
    -0.06
    jsp
    -0.06
    .tabs
    -0.06
    .seek
    -0.06
    ();↵↵↵
    -0.06
    ]={
    -0.06
    plemented
    -0.06
    >
↵
↵
    -0.06
     kurulan
    -0.06
    POSITIVE LOGITS
    /questions
    0.07
     Autism
    0.06
     patriot
    0.06
    payer
    0.06
    'e
    0.06
     bingo
    0.06
    Street
    0.06
    .api
    0.06
    _PATTERN
    0.06
     iam
    0.06
    Activations Density 0.004%

    No Known Activations