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. 53135
    Prev
    Next
    INDEX
    Explanations

    mini

    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
     pervasive
    -0.07
     STDOUT
    -0.06
     أمر
    -0.06
     mücadele
    -0.06
     squarely
    -0.06
     skupina
    -0.06
     ranked
    -0.06
     делать
    -0.06
    ่เป
    -0.06
     vile
    -0.06
    POSITIVE LOGITS
     mini
    0.19
     Mini
    0.16
    Mini
    0.16
    -mini
    0.11
    mini
    0.11
     miniature
    0.10
    _mini
    0.09
    ini
    0.08
    limitations
    0.07
    _J
    0.07
    Activations Density 0.006%

    No Known Activations