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. 44390
    Prev
    Next
    INDEX
    Explanations

    references to cost analysis and acquisition processes

    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
    cheid
    -0.07
    ectors
    -0.07
     gön
    -0.07
     Animalia
    -0.06
    agens
    -0.06
    elda
    -0.06
    abox
    -0.06
     Duis
    -0.06
    -git
    -0.06
    rett
    -0.06
    POSITIVE LOGITS
     FAR
    0.14
     DF
    0.11
     contractor
    0.11
     Contractor
    0.11
     contracting
    0.11
     Defense
    0.10
     subcontract
    0.09
    Contract
    0.09
     Contract
    0.09
     contractors
    0.09
    Activations Density 0.017%

    No Known Activations