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. 44134
    Prev
    Next
    INDEX
    Explanations

    symbols or terms related to mathematical or scientific notation

    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
    /Area
    -0.07
     Pakistani
    -0.07
    .Cluster
    -0.07
    otland
    -0.06
    elez
    -0.06
     Lahore
    -0.06
     Pakistan
    -0.06
    Pakistan
    -0.06
     Ñģон
    -0.06
    andbox
    -0.06
    POSITIVE LOGITS
     Sad
    0.15
    Sad
    0.12
     sad
    0.11
     river
    0.11
     rivers
    0.10
     River
    0.10
    river
    0.09
     Rally
    0.09
     Save
    0.08
     Mystic
    0.08
    Activations Density 0.002%

    No Known Activations