© 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. 74663
    Prev
    Next
    INDEX
    Explanations

    technical terms related to database queries and cost analysis

    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
    usan
    -0.06
    rens
    -0.06
     import
    -0.06
    issors
    -0.06
    atron
    -0.05
    punk
    -0.05
     ?
    -0.05
    erse
    -0.05
    rab
    -0.05
    owan
    -0.05
    POSITIVE LOGITS
    /cop
    0.09
    _DDR
    0.08
    _NC
    0.07
    ssql
    0.07
    /slider
    0.07
    Äįel
    0.07
    æĹ
    0.07
    _ENSURE
    0.07
    DBC
    0.07
    codegen
    0.07
    Activations Density 0.023%

    No Known Activations