© 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. 55756
    Prev
    Next
    INDEX
    Explanations

    rule violation consequences

    np_max-act · gemini-2.0-flash

    The neuron fires on conditional “if…then” enforcement language—that is, clauses warning of penalties or removal for rule violations.

    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
     acupuncture
    -0.07
    award
    -0.06
    adapt
    -0.06
     Normalize
    -0.06
     IMG
    -0.06
    _history
    -0.06
    paid
    -0.06
    corn
    -0.06
     glossy
    -0.06
     ade
    -0.06
    POSITIVE LOGITS
    цвет
    0.08
    лся
    0.07
    洁
    0.06
    stash
    0.06
     sécurité
    0.06
    Rather
    0.06
    信
    0.06
    athed
    0.06
     pleas
    0.06
     відпов
    0.06
    Activations Density 0.105%

    No Known Activations