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. 23-RESID-POST-AA
    6. 104073
    Prev
    Next
    INDEX
    Explanations

    Firebase databases

    np_max-act-logits · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    andyrdt/saes-llama-3.1-8b-instruct/resid_post_layer_23/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.23.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    Hierarchy
    -0.07
     discounts
    -0.07
     техничес
    -0.07
    Requested
    -0.07
    حية
    -0.07
    _latest
    -0.06
    Rs
    -0.06
    _requested
    -0.06
     Displays
    -0.06
     uçak
    -0.06
    POSITIVE LOGITS
    CAL
    0.06
    "Oh
    0.06
    .</
    0.06
    -play
    0.06
    imeline
    0.06
     skeptic
    0.06
    ُن
    0.06
    \App
    0.06
    Standing
    0.06
    zf
    0.06
    Activations Density 0.029%

    No Known Activations