© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 121596
    Prev
    Next
    INDEX
    Explanations

    somewhat

    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
     slated
    -0.07
     viscosity
    -0.06
     nông
    -0.06
    .Categories
    -0.06
     glorious
    -0.06
    NIC
    -0.06
     invit
    -0.06
     rats
    -0.06
    innerText
    -0.06
    rosso
    -0.06
    POSITIVE LOGITS
     somewhat
    0.33
    ewhat
    0.23
     sembl
    0.07
     somew
    0.07
     zcela
    0.07
    /event
    0.07
    awesome
    0.06
    som
    0.06
     несколько
    0.06
    有点
    0.06
    Activations Density 0.002%

    No Known Activations