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. 44284
    Prev
    Next
    INDEX
    Explanations

    terms related to programming objects and their properties

    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
     from
    -0.09
     for
    -0.09
     in
    -0.09
     on
    -0.09
     with
    -0.09
     to
    -0.09
     In
    -0.09
     and
    -0.09
     N
    -0.08
     by
    -0.08
    POSITIVE LOGITS
    _you
    0.13
    _Tis
    0.12
    _that
    0.12
    _almost
    0.11
    _while
    0.11
    _again
    0.11
    _most
    0.11
    _every
    0.11
    _within
    0.11
    _but
    0.11
    Activations Density 0.074%

    No Known Activations