© 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. 25734
    Prev
    Next
    INDEX
    Explanations

    :

    np_max-act · gemini-2.0-flash

    technical terms related to debugging and memory management in programming.

    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
     органов
    -0.07
     gắng
    -0.07
    meldung
    -0.06
     Say
    -0.06
     dicho
    -0.06
     yön
    -0.06
     stroll
    -0.06
     ge
    -0.06
     до
    -0.06
    ống
    -0.06
    POSITIVE LOGITS
    เคย
    0.06
     unsub
    0.06
     [+
    0.06
    273
    0.06
    нимает
    0.06
    .Hit
    0.06
    的一
    0.06
    "],"
    0.06
    .some
    0.06
     Evalu
    0.06
    Activations Density 0.002%

    No Known Activations