© 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. 125917
    Prev
    Next
    INDEX
    Explanations

    terms related to proposals and grant-writing 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
    ereg
    -0.07
    _DP
    -0.07
    _FS
    -0.07
    èĢ³
    -0.07
    ç§
    -0.07
    .Cryptography
    -0.06
     Arbit
    -0.06
    spath
    -0.06
     WARRANT
    -0.06
    Poll
    -0.06
    POSITIVE LOGITS
     bid
    0.09
     Bid
    0.09
     winning
    0.08
    -winning
    0.07
     bids
    0.07
    zzle
    0.07
    oproject
    0.07
    .writeString
    0.07
     Winning
    0.07
     awarded
    0.07
    Activations Density 0.008%

    No Known Activations