© 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. 11-RESID-POST-AA
    6. 85713
    Prev
    Next
    INDEX
    Explanations

    newline characters

    np_max-act · gemini-2.0-flash

    the presence of backslash characters as directory separators in file paths (i.e. Windows‐style paths).

    oai_token-act-pair · o4-miniTriggered by @xinyanhu8
    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
     노하우
    -0.08
    Hamilton
    -0.07
    implementation
    -0.07
     Wayne
    -0.07
     Cait
    -0.07
     Alonso
    -0.07
    -runner
    -0.07
     Wilson
    -0.07
    Mahon
    -0.07
     steroid
    -0.07
    POSITIVE LOGITS
     الح
    0.08
    л
    0.07
     Т
    0.07
    \F
    0.07
     Sleeping
    0.07
     lớp
    0.07
    ocup
    0.07
    ้า
    0.07
    .Val
    0.07
    \
    0.06
    Activations Density 0.013%

    No Known Activations