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. 44170
    Prev
    Next
    INDEX
    Explanations

    mathematical symbols and notations

    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
     tuyá»ĥn
    -0.07
    ũi
    -0.07
    æŁĵ
    -0.07
    igon
    -0.06
    obo
    -0.06
    šek
    -0.06
    .EventQueue
    -0.06
     Quarry
    -0.06
    ingleton
    -0.06
    GMEM
    -0.06
    POSITIVE LOGITS
     surge
    0.15
     Surge
    0.13
     SPD
    0.12
     spike
    0.11
     protector
    0.11
     protection
    0.11
     transient
    0.11
     MOV
    0.11
     Spike
    0.10
     suppress
    0.10
    Activations Density 0.009%

    No Known Activations