Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 87571
    Prev
    Next
    INDEX
    Explanations

    dates or references to specific times

    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
    ense
    -0.08
    ess
    -0.07
    ysis
    -0.07
    koa
    -0.07
    yard
    -0.07
    ledo
    -0.07
    hec
    -0.07
    genic
    -0.07
    enez
    -0.06
    ema
    -0.06
    POSITIVE LOGITS
    quis
    0.08
    ÙħÙĪÙĦ
    0.08
    inel
    0.07
    eri
    0.07
    low
    0.07
    hap
    0.07
    quee
    0.07
    iscal
    0.07
    วม
    0.07
    isch
    0.07
    Activations Density 0.019%

    No Known Activations