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. 15-RESID-POST-AA
    6. 37479
    Prev
    Next
    INDEX
    Explanations
    No Explanations Found
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_15/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.15.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     ambient
    -0.06
     defined
    -0.06
     expected
    -0.06
     INTERNATIONAL
    -0.06
     smo
    -0.06
    遍
    -0.06
    /connect
    -0.06
    回答
    -0.06
     Aura
    -0.06
    Begin
    -0.05
    POSITIVE LOGITS
    UNC
    0.07
     Gates
    0.06
    iterate
    0.06
     GRA
    0.06
    _PR
    0.06
    ı
    0.06
    razione
    0.06
    DownList
    0.06
    _YUV
    0.06
    ccoli
    0.06
    Activations Density 0.135%

    No Known Activations