Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44374
    Prev
    Next
    INDEX
    Explanations

    details related to visual descriptions and perspectives

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    cerebras/SlimPajama-627B
    No Configuration Found
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    alom
    -0.07
    ãn
    -0.06
    ÑĨÑĮкий
    -0.06
    cretion
    -0.06
     eskort
    -0.06
    MAND
    -0.06
     HOLDER
    -0.06
     |_|
    -0.06
    etur
    -0.06
     MPG
    -0.06
    POSITIVE LOGITS
     speaker
    0.11
     setting
    0.09
    speaker
    0.09
     narrator
    0.09
     tone
    0.09
     Tone
    0.08
     Theme
    0.08
     theme
    0.08
     Speaker
    0.08
     use
    0.08
    Activations Density 0.048%

    No Known Activations