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. 43707
    Prev
    Next
    INDEX
    Explanations

    references to historical events and their significance

    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
    ayet
    -0.08
    esture
    -0.06
    stå
    -0.06
    isode
    -0.06
    synthesize
    -0.06
    DTD
    -0.06
    illance
    -0.06
    azon
    -0.06
    :animated
    -0.06
    mittel
    -0.06
    POSITIVE LOGITS
     rh
    0.11
     repeating
    0.11
     records
    0.11
     judge
    0.10
     repeats
    0.10
     repeated
    0.09
     Rh
    0.09
     record
    0.09
     repeat
    0.09
     rhyme
    0.09
    Activations Density 0.011%

    No Known Activations