© 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. 78
    Prev
    Next
    INDEX
    Explanations

    keywords related to music and film industry references

    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
    vale
    -0.06
    riel
    -0.06
    anio
    -0.06
    mony
    -0.06
     Baptist
    -0.06
     rele
    -0.06
    ruba
    -0.06
    ãĥŃãĥ¼
    -0.06
     plain
    -0.06
    icas
    -0.06
    POSITIVE LOGITS
    ling
    0.07
    quirer
    0.07
    sett
    0.06
     ç·
    0.06
    Ïĥη
    0.06
     Governor
    0.06
    -await
    0.06
    ë¥
    0.06
    sets
    0.06
    yssey
    0.06
    Activations Density 0.056%

    No Known Activations