© 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. 94117
    Prev
    Next
    INDEX
    Explanations

    phrases or concepts related to the pinnacle or peak of quality or achievement

    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
    cstdio
    -0.07
    getClient
    -0.07
    ftype
    -0.07
    asks
    -0.07
    rál
    -0.06
    าà¸į
    -0.06
     MacDonald
    -0.06
    cmds
    -0.06
    engkap
    -0.06
    audi
    -0.06
    POSITIVE LOGITS
     store
    0.07
     stores
    0.07
     liquid
    0.07
    /browse
    0.07
    store
    0.06
    PROTO
    0.06
    æĥ
    0.06
    liquid
    0.06
     browsing
    0.06
     inventory
    0.06
    Activations Density 0.000%

    No Known Activations