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. 44149
    Prev
    Next
    INDEX
    Explanations

    instances of the word "most" and variations thereof

    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
     Various
    -0.10
     some
    -0.10
     a
    -0.09
     several
    -0.08
     both
    -0.08
     various
    -0.08
    Various
    -0.08
    æĽ´å¤ļ
    -0.08
     an
    -0.08
     Several
    -0.07
    POSITIVE LOGITS
     of
    0.20
    /all
    0.19
     importantly
    0.17
     likely
    0.14
    afa
    0.13
     notably
    0.12
     if
    0.12
    everything
    0.11
    likely
    0.11
    of
    0.11
    Activations Density 0.032%

    No Known Activations