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. 43953
    Prev
    Next
    INDEX
    Explanations

    references to digital submissions and photographic content

    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
    lsen
    -0.07
     doctrines
    -0.06
    protocols
    -0.06
     Tape
    -0.06
     nowrap
    -0.06
    ogne
    -0.06
     Diseases
    -0.06
    .Charting
    -0.06
    StringEncoding
    -0.06
    overe
    -0.06
    POSITIVE LOGITS
     shots
    0.16
     snaps
    0.15
     pics
    0.13
     images
    0.13
     snapshots
    0.12
     pictures
    0.12
     photos
    0.12
     pix
    0.12
     candid
    0.12
     cand
    0.11
    Activations Density 0.050%

    No Known Activations