© 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. 105414
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    references to geographical locations and related context.

    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
     niž
    -0.07
     čt
    -0.07
     बदल
    -0.06
    сий
    -0.06
    юсь
    -0.06
     nale
    -0.06
    -testing
    -0.06
     сни
    -0.06
     �
    -0.06
     skupiny
    -0.06
    POSITIVE LOGITS
    (:,
    0.07
    =G
    0.07
    股票
    0.07
     Vehicles
    0.06
     *))
    0.06
    ===
    0.06
    <|begin_of_text|>
    0.06
    **)&
    0.06
    :)
    0.06
     __(
    0.06
    Activations Density 0.001%

    No Known Activations