Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. Andy Arditi · Finding Misaligned Persona Features in Open-Weight Models
    3. Llama3.1-8B-IT (Instruct)
    4. Resid Post - 131k
    5. 3-RESID-POST-AA
    6. 94792
    Prev
    Next
    INDEX
    Explanations

    thyrotropin

    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_3/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.3.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     киш
    -0.07
    ById
    -0.07
     году
    -0.06
    );↵↵↵
    -0.06
    *dt
    -0.06
    IFIC
    -0.06
    isión
    -0.06
     подт
    -0.06
     выполн
    -0.06
     fart
    -0.06
    POSITIVE LOGITS
    rop
    0.31
    ROP
    0.19
    роп
    0.14
    rops
    0.11
    throp
    0.11
    otropic
    0.11
    ropy
    0.10
    ropa
    0.09
     trop
    0.09
     rop
    0.09
    Activations Density 0.009%

    No Known Activations