© 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 EvalsExportsinterp-engineNEWAPI 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. 95506
    Prev
    Next
    INDEX
    Explanations

    content related to sports news and opinions

    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
    ãģĵãģĿ
    -0.08
     fucking
    -0.06
    aniel
    -0.06
    ãģ°ãģĭãĤĬ
    -0.06
    .INSTANCE
    -0.06
    ÂĢÂĻ
    -0.06
    Writes
    -0.06
    ÑĴ
    -0.06
    Ä©nh
    -0.06
     instead
    -0.06
    POSITIVE LOGITS
     Uncategorized
    0.11
    788
    0.07
    790
    0.07
    614
    0.07
    583
    0.07
    740
    0.07
    708
    0.07
    989
    0.07
    midd
    0.07
    669
    0.06
    Activations Density 0.004%

    No Known Activations