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. 43383
    Prev
    Next
    INDEX
    Explanations

    information related to cancer research and diagnosis

    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
    adol
    -0.07
    sembly
    -0.06
     sugars
    -0.06
    autop
    -0.06
     pestic
    -0.06
    isos
    -0.06
    ilate
    -0.06
     Constructs
    -0.06
    zym
    -0.06
    _rat
    -0.06
    POSITIVE LOGITS
     driver
    0.14
    driver
    0.12
     Driver
    0.11
    Driver
    0.11
    -driver
    0.11
     drivers
    0.10
     mut
    0.10
     actionable
    0.10
     som
    0.09
    .driver
    0.09
    Activations Density 0.013%

    No Known Activations