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. 11-RESID-POST-AA
    6. 88410
    Prev
    Next
    INDEX
    Explanations

    commas

    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_11/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.11.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     Framework
    -0.08
     IP
    -0.07
    ”↵↵
    -0.07
    Compound
    -0.06
     Rad
    -0.06
     enhancement
    -0.06
    !”↵↵
    -0.06
    _H
    -0.06
    ikal
    -0.06
     Hydro
    -0.06
    POSITIVE LOGITS
     nombreux
    0.06
     pus
    0.06
     харч
    0.06
     salsa
    0.06
     incess
    0.06
    enuine
    0.06
     معل
    0.06
     espacio
    0.06
    lobe
    0.06
    .setOutput
    0.06
    Activations Density 0.022%

    No Known Activations