© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 15-LLAMASCOPE-RES-131K
    11. 103109
    Prev
    Next
    INDEX
    Explanations

    references to jubilees and significant celebrations

    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
    yb
    -0.09
    iggs
    -0.07
    ETA
    -0.07
    ayas
    -0.07
    aris
    -0.07
    ebo
    -0.07
    Äįi
    -0.07
    кеÑĤ
    -0.06
    aq
    -0.06
    arin
    -0.06
    POSITIVE LOGITS
    hammer
    0.07
    irement
    0.07
    mares
    0.07
    atory
    0.07
    Ð¤ÐĽ
    0.06
    perator
    0.06
    ante
    0.06
    ForRow
    0.06
    zed
    0.06
    ataire
    0.06
    Activations Density 0.002%

    No Known Activations