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. 44157
    Prev
    Next
    INDEX
    Explanations

    symbols and parameters related to mathematical or scientific contexts

    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
    quee
    -0.06
    _hooks
    -0.06
    elm
    -0.06
    àµįà´
    -0.05
     volupt
    -0.05
     cigar
    -0.05
    datagrid
    -0.05
     softened
    -0.05
    tensorflow
    -0.05
    éĻ©
    -0.05
    POSITIVE LOGITS
     communication
    0.11
     message
    0.11
     gossip
    0.10
     broadcast
    0.10
     Communication
    0.10
    Communication
    0.10
     synchronous
    0.10
     messages
    0.09
     processors
    0.09
     Byz
    0.09
    Activations Density 0.007%

    No Known Activations