© 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. 18158
    Prev
    Next
    INDEX
    Explanations

    colons

    np_max-act · gemini-2.0-flash

    structured text formatting with headings or numbered points in instructional content.

    oai_token-act-pair · claude-3-7-sonnet-20250219Triggered by @chuloivawork

    clinical terms related to mental health and psychosis.

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

    decimal numeric values (floating-point style numbers) embedded in the text

    oai_token-act-pair · gpt-5Triggered by @vetterc0
    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
     дод
    -0.06
     scl
    -0.06
     null
    -0.06
    .sub
    -0.06
    cdb
    -0.06
    .LINE
    -0.06
    ajas
    -0.06
     ->↵
    -0.06
    _GenericClass
    -0.06
    884
    -0.06
    POSITIVE LOGITS
    -European
    0.08
    ım
    0.07
    Finder
    0.07
    ↵
    0.06
    เปอร
    0.06
    ัค
    0.06
     důvod
    0.06
    .forms
    0.06
     Vì
    0.06
     Cats
    0.06
    Activations Density 0.090%

    No Known Activations