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. 15-RESID-POST-AA
    6. 41485
    Prev
    Next
    INDEX
    Explanations

    hypothetical scenarios

    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
    _capacity
    -0.07
     REPLACE
    -0.06
    уста
    -0.06
     Heroes
    -0.06
    Custom
    -0.06
    "><
    -0.06
    torch
    -0.06
     два
    -0.06
     kterou
    -0.06
    Twenty
    -0.06
    POSITIVE LOGITS
     Klo
    0.07
    .pkg
    0.07
    aket
    0.07
    ียง
    0.07
    >*</
    0.06
    .Patient
    0.06
    _players
    0.06
    orthand
    0.06
    ộp
    0.06
    weep
    0.06
    Activations Density 0.114%

    No Known Activations