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. 11528
    Prev
    Next
    INDEX
    Explanations

    references to scientific studies and their findings

    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
    armacy
    -0.07
    ustum
    -0.07
    WN
    -0.06
    opol
    -0.06
    Streamer
    -0.06
    HeaderValue
    -0.06
    anches
    -0.06
    HWND
    -0.06
    .gallery
    -0.06
    .getWriter
    -0.06
    POSITIVE LOGITS
     Fors
    0.14
     Stud
    0.11
     experiment
    0.10
     Research
    0.10
     Experiment
    0.10
     Unters
    0.10
     method
    0.09
     research
    0.09
     analy
    0.09
     Method
    0.09
    Activations Density 0.012%

    No Known Activations