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. 43954
    Prev
    Next
    INDEX
    Explanations

    references to books and reading experiences

    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
    bullet
    -0.08
    lobby
    -0.07
    usercontent
    -0.07
     ".$_
    -0.07
    alyzer
    -0.07
    URA
    -0.07
    DV
    -0.07
    odelist
    -0.07
    mil
    -0.06
    uco
    -0.06
    POSITIVE LOGITS
     Guards
    0.10
     Tiffany
    0.10
     Sour
    0.09
     Hog
    0.09
     Reaper
    0.09
     Wy
    0.09
     Disc
    0.08
     Feet
    0.08
     Equal
    0.08
     Moist
    0.08
    Activations Density 0.027%

    No Known Activations