© 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. 29219
    Prev
    Next
    INDEX
    Explanations

    words that signify an official or formal communication

    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
    ÃĸL
    -0.07
    its
    -0.06
    ansas
    -0.06
     prostituerade
    -0.06
    anz
    -0.06
    à¹ģห
    -0.06
    tie
    -0.06
    Ä°Åŀ
    -0.06
    ublice
    -0.06
    ãĥ£
    -0.06
    POSITIVE LOGITS
     which
    0.11
    which
    0.09
    .which
    0.09
    Which
    0.08
     Which
    0.08
     WHICH
    0.08
     cui
    0.07
     która
    0.07
    .react
    0.06
    uh
    0.06
    Activations Density 0.014%

    No Known Activations