© 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. 20943
    Prev
    Next
    INDEX
    Explanations

    /schema

    np_max-act · gemini-2.0-flash

    text related to software licensing and package metadata.

    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
     кноп
    -0.08
     version
    -0.07
    [level
    -0.06
     distances
    -0.06
     confisc
    -0.06
    	btn
    -0.06
     vampires
    -0.06
     olmadığını
    -0.06
    (Address
    -0.06
     "=
    -0.06
    POSITIVE LOGITS
    imli
    0.07
    �
    0.07
    وبی
    0.06
    .ToDouble
    0.06
    ographic
    0.06
     powerhouse
    0.06
     datum
    0.06
    ishment
    0.06
    Ec
    0.06
    payer
    0.06
    Activations Density 0.008%

    No Known Activations