© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 126337
    Prev
    Next
    INDEX
    Explanations

    themes related to academic and professional networking opportunities

    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
    BindingUtil
    -0.09
    argout
    -0.09
     blockIdx
    -0.08
    ampp
    -0.08
    .Actions
    -0.08
     æ®
    -0.08
    ulace
    -0.08
    ilden
    -0.08
    ameda
    -0.08
    ekil
    -0.08
    POSITIVE LOGITS
     potential
    0.11
     future
    0.11
     network
    0.09
     later
    0.09
     potentially
    0.09
     possible
    0.08
     mutually
    0.08
     further
    0.08
     networking
    0.07
     Network
    0.07
    Activations Density 0.027%

    No Known Activations