© 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
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 11-RESID-POST-AA
    6. 52254
    Prev
    Next
    INDEX
    Explanations

    requests and instructions

    np_max-act · gemini-2.0-flash

    mentions of countries and their associated sentiments in product reviews.

    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
     dilemma
    -0.07
    yre
    -0.07
     injector
    -0.06
     ambitious
    -0.06
     Fare
    -0.06
     shoulders
    -0.06
     legendary
    -0.06
     redeemed
    -0.06
    Done
    -0.06
     retained
    -0.06
    POSITIVE LOGITS
     [&](
    0.07
     ));↵
    0.07
     Monsanto
    0.07
     кисл
    0.07
     GIVEN
    0.06
    (math
    0.06
    출장샵
    0.06
    _indx
    0.06
    =line
    0.06
    <Real
    0.06
    Activations Density 0.047%

    No Known Activations