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. 43920
    Prev
    Next
    INDEX
    Explanations

    words or symbols that represent unique or distinctive concepts

    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
     the
    -0.08
     A
    -0.08
     D
    -0.07
     
    -0.07
     final
    -0.07
     (
    -0.07
     De
    -0.07
     The
    -0.07
     another
    -0.07
     and
    -0.07
    POSITIVE LOGITS
    Body
    0.09
    Cell
    0.09
    Last
    0.09
    One
    0.08
    Left
    0.08
    á»ijn
    0.08
    chwitz
    0.08
    íĥľ
    0.08
    opsis
    0.08
    oltip
    0.07
    Activations Density 0.001%

    No Known Activations