© 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. 34927
    Prev
    Next
    INDEX
    Explanations

    punctuation

    np_max-act · gemini-2.0-flash

    descriptions of graphic design and marketing services.

    oai_token-act-pair · gpt-4o-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
     doğrudan
    -0.07
     peanut
    -0.06
     Laurie
    -0.06
    ivot
    -0.06
    ucky
    -0.06
     survives
    -0.06
     쉬
    -0.06
    >Show
    -0.06
     Odyssey
    -0.06
     다양한
    -0.06
    POSITIVE LOGITS
     Ц
    0.07
    zs
    0.06
    Wr
    0.06
    tras
    0.06
     __________________________________
    0.06
    ↵ ↵
    0.06
     =================================================================================
    0.06
     Shot
    0.06
     stagn
    0.06
    ieties
    0.06
    Activations Density 0.030%

    No Known Activations