© 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. 93920
    Prev
    Next
    INDEX
    Explanations

    descriptor

    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
    lo
    -0.07
    jest
    -0.07
     organis
    -0.07
    .ResponseWriter
    -0.07
    opyright
    -0.07
    率
    -0.06
     résult
    -0.06
     knowingly
    -0.06
     antenn
    -0.06
    (coord
    -0.06
    POSITIVE LOGITS
    Descriptor
    0.06
     recogn
    0.06
     değiştir
    0.06
    <F
    0.06
    ео
    0.06
     Actor
    0.06
     """",↵
    0.06
     scaled
    0.06
     mrt
    0.06
    œur
    0.06
    Activations Density 0.183%

    No Known Activations