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. 43622
    Prev
    Next
    INDEX
    Explanations

    dates and specific times

    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
    ('').
    -0.07
    vyk
    -0.06
    ().↵
    -0.06
    but
    -0.06
    ENCHMARK
    -0.06
    ãĢĤ(
    -0.06
     WHICH
    -0.06
     but
    -0.06
    onde
    -0.06
    idir
    -0.06
    POSITIVE LOGITS
     we
    0.15
     it
    0.14
     there
    0.13
     they
    0.12
     alone
    0.10
     a
    0.10
     an
    0.09
     another
    0.09
     she
    0.09
     the
    0.09
    Activations Density 0.047%

    No Known Activations