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. 22-LLAMASCOPE-RES-131K
    6. 5683
    Prev
    Next
    INDEX
    Explanations

    expressions of gratitude

    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
    illy
    -0.07
    ini
    -0.06
    itor
    -0.06
    iff
    -0.06
    IRE
    -0.06
    gatsby
    -0.06
     Maar
    -0.06
    iling
    -0.06
    ire
    -0.06
    ühr
    -0.06
    POSITIVE LOGITS
    atables
    0.07
    _nt
    0.07
     again
    0.06
    alue
    0.06
    istring
    0.06
    æ¸
    0.06
    ãĥ¼ãĥĸ
    0.06
    istrovstvÃŃ
    0.06
    'Brien
    0.06
    [".
    0.06
    Activations Density 0.001%

    No Known Activations