© 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. 76694
    Prev
    Next
    INDEX
    Explanations

    indicators of statistical or numerical data

    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
    ometer
    -0.06
     (~
    -0.06
     alc
    -0.06
    ç
    -0.06
    ym
    -0.06
    turned
    -0.05
     ìĦľë¡ľ
    -0.05
     Counts
    -0.05
     precinct
    -0.05
     ad
    -0.05
    POSITIVE LOGITS
     figure
    0.09
    isman
    0.08
    _UNUSED
    0.08
    ipt
    0.08
    chwitz
    0.07
    ranÃŃ
    0.07
     figures
    0.07
    ãĥ¼ãĥĭ
    0.07
    figure
    0.07
    igure
    0.07
    Activations Density 0.030%

    No Known Activations