© 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. 45465
    Prev
    Next
    INDEX
    Explanations

    phrase

    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
     okolí
    -0.06
    (lower
    -0.06
    setOnClickListener
    -0.06
    >y
    -0.06
     CUDA
    -0.06
     correctness
    -0.06
    ่ละ
    -0.06
    Center
    -0.06
    「你
    -0.06
    getModel
    -0.06
    POSITIVE LOGITS
     phrase
    0.09
    phrase
    0.07
     Phrase
    0.07
     přiv
    0.07
    Expression
    0.07
     trụ
    0.07
     hesitant
    0.06
     rationale
    0.06
    프로
    0.06
     предпоч
    0.06
    Activations Density 0.011%

    No Known Activations