© 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. 112024
    Prev
    Next
    INDEX
    Explanations

    to

    np_max-act · gemini-2.0-flash
    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
     理
    -0.07
    mscorlib
    -0.06
    人が
    -0.06
     incompetence
    -0.06
    women
    -0.06
     모습
    -0.06
     důležité
    -0.06
    mall
    -0.06
    ัคร
    -0.06
    Adam
    -0.06
    POSITIVE LOGITS
     provisions
    0.07
     correcting
    0.06
    рабат
    0.06
    alardan
    0.06
    320
    0.06
     verbally
    0.06
     appendix
    0.06
    _tok
    0.06
     allure
    0.06
     Condition
    0.06
    Activations Density 0.026%

    No Known Activations