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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    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. 61596
    Prev
    Next
    INDEX
    Explanations

    to

    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_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
    "d
    -0.07
     boarding
    -0.07
    <Resource
    -0.07
     damages
    -0.06
    十二
    -0.06
     ihnen
    -0.06
     пло
    -0.06
     kosher
    -0.06
     druž
    -0.06
    Shows
    -0.06
    POSITIVE LOGITS
    .setInput
    0.07
    eshire
    0.06
     maxx
    0.06
    .AppendText
    0.06
    =(↵
    0.06
     обычно
    0.06
    concat
    0.06
    .vx
    0.06
    .Array
    0.06
    ái
    0.06
    Activations Density 0.015%

    No Known Activations