© 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. 76847
    Prev
    Next
    INDEX
    Explanations

    discussions of degrees of truth or extent regarding phenomena and experiences

    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
    orman
    -0.07
    aml
    -0.06
    stm
    -0.06
    holm
    -0.06
    ektor
    -0.06
    874
    -0.06
    mach
    -0.06
    usch
    -0.06
    reate
    -0.06
    zı
    -0.06
    POSITIVE LOGITS
     extent
    0.10
     actually
    0.08
    extent
    0.08
    ç¨ĭ度
    0.07
     extents
    0.07
     versus
    0.07
     noreferrer
    0.07
     degree
    0.06
    ÄĻż
    0.06
     vs
    0.06
    Activations Density 0.027%

    No Known Activations