© 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
    7. Resid Post - 131k
    9. 3-RESID-POST-AA
    11. 121690
    Prev
    Next
    INDEX
    Explanations

    w

    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
     chatt
    -0.07
     ánh
    -0.06
     rushed
    -0.06
     hap
    -0.06
     workshops
    -0.06
     tess
    -0.06
    ượng
    -0.06
     Tome
    -0.06
     intersection
    -0.06
     pik
    -0.06
    POSITIVE LOGITS
     FW
    0.17
    FW
    0.13
    fw
    0.13
     fw
    0.12
    _fw
    0.09
    _FW
    0.09
    /fw
    0.08
    (GLFW
    0.08
    -fw
    0.07
    WS
    0.07
    Activations Density 0.005%

    No Known Activations