© 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. 30609
    Prev
    Next
    INDEX
    Explanations

    use

    np_max-act · gemini-2.0-flash

    financial expenditures and budget-related metrics.

    oai_token-act-pair · gpt-4o-miniTriggered by @xinyanhu8

    The neuron detects boilerplate legal disclaimers about “personal use” or reproduction rights in document footers.

    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
    apult
    -0.06
    Strong
    -0.06
    elian
    -0.06
    .direct
    -0.06
    ults
    -0.06
    �
    -0.06
    Birth
    -0.06
    ustry
    -0.06
    iệc
    -0.06
    urdy
    -0.06
    POSITIVE LOGITS
     hashtags
    0.07
     rooft
    0.07
     çalışan
    0.07
     Olomou
    0.07
    ुछ
    0.06
     زمانی
    0.06
    0.06
    己
    0.06
    Kon
    0.06
    dın
    0.06
    Activations Density 0.003%

    No Known Activations