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. 19-RESID-POST-AA
    6. 84096
    Prev
    Next
    INDEX
    Explanations

    Billy

    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_19/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.19.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    getDisplay
    -0.07
     XmlNode
    -0.06
    呼ば
    -0.06
    treeview
    -0.06
    =context
    -0.06
     wd
    -0.06
    Actually
    -0.06
     Hoffman
    -0.06
     mattered
    -0.06
    Caller
    -0.06
    POSITIVE LOGITS
     Billy
    0.08
    ètre
    0.07
    Billy
    0.07
    /header
    0.07
    /*.
    0.07
    iph
    0.06
     "\\
    0.06
    881
    0.06
     bin
    0.06
     Len
    0.06
    Activations Density 0.001%

    No Known Activations