© 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. 19-RESID-POST-AA
    11. 73407
    Prev
    Next
    INDEX
    Explanations

    Non-English characters

    np_max-act-logits · gemini-2.0-flashTriggered by @majianfei030706
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     rumors
    -0.07
     bombers
    -0.06
    ализа
    -0.06
     Bom
    -0.06
    уры
    -0.06
     Osama
    -0.06
    _:
    -0.06
    짜
    -0.06
    最大
    -0.06
     bur
    -0.06
    POSITIVE LOGITS
     통합
    0.06
    :req
    0.06
    讨
    0.06
     cong
    0.06
     прор
    0.06
     partnership
    0.06
    focus
    0.06
    prix
    0.06
    =format
    0.06
    hana
    0.06
    Activations Density 0.000%

    No Known Activations