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. 7-RESID-POST-AA
    6. 35308
    Prev
    Next
    INDEX
    Explanations

    aftermath of

    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_7/trainer_1
    Dataset (Dashboard)
    Various
    Features
    131,072
    Data Type
    float32
    Hook Name
    blocks.7.hook_resid_post
    Architecture
    standard
    Context Size
    1,024
    Dataset
    monology/pile-uncopyrighted
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
     instinct
    -0.07
     lasers
    -0.07
    Forest
    -0.06
     Decoration
    -0.06
     ゙
    -0.06
     ف
    -0.06
     Роз
    -0.06
     gsi
    -0.06
     Design
    -0.06
    .Serializable
    -0.06
    POSITIVE LOGITS
     aftermath
    0.14
     wake
    0.08
     fallout
    0.07
    Feed
    0.06
    _pdata
    0.06
    ftime
    0.06
     Samples
    0.06
    ματα
    0.06
    tfoot
    0.06
    Wall
    0.06
    Activations Density 0.004%

    No Known Activations