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

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 78381
    Prev
    Next
    INDEX
    Explanations

    references to television programming and series, particularly those related to Mexican television and NCAA football

    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
     Spr
    -0.07
    fund
    -0.07
    tü
    -0.07
    à¥Ģल
    -0.06
    aturing
    -0.06
     Holt
    -0.06
    ÑĢаÑĩ
    -0.06
    [__
    -0.06
    Spr
    -0.06
    å°Ĥ
    -0.06
    POSITIVE LOGITS
    rike
    0.07
    insky
    0.07
    ró
    0.07
    бо
    0.06
    ginas
    0.06
    UTIL
    0.06
    agate
    0.06
    ãĤ·ãĥ¼
    0.06
    URY
    0.06
    LOUR
    0.06
    Activations Density 0.003%

    No Known Activations