© 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. 41422
    Prev
    Next
    INDEX
    Explanations

    improvements and corrections

    np_max-act · gemini-2.0-flash

    formal and precise language suitable for professional or academic contexts.

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

    It activates on numeric values (especially decimal numbers) appearing in the text.

    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
     blok
    -0.08
    .Day
    -0.06
     Clause
    -0.06
     efficiently
    -0.06
     isAdmin
    -0.06
    athing
    -0.06
    ']+
    -0.06
     treasure
    -0.06
    -effective
    -0.06
    洁
    -0.06
    POSITIVE LOGITS
    [idx
    0.08
    olta
    0.08
    AppDelegate
    0.08
    iyle
    0.07
     �
    0.06
     coff
    0.06
     đấu
    0.06
     Hindus
    0.06
    ]-'
    0.06
     церков
    0.06
    Activations Density 0.020%

    No Known Activations