© 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. 29161
    Prev
    Next
    INDEX
    Explanations

    expressions and phrases indicating the need for communication or clarification

    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
    SSERT
    -0.09
    ruk
    -0.08
    enet
    -0.08
    _UUID
    -0.07
    htdocs
    -0.07
    ãĥ¼ãĥŀ
    -0.07
    reon
    -0.07
    ohana
    -0.07
    dez
    -0.07
    iyon
    -0.07
    POSITIVE LOGITS
     accordingly
    0.09
     reflected
    0.07
    fact
    0.07
     fact
    0.07
     thereof
    0.06
     indicated
    0.06
     flagged
    0.06
    442
    0.06
     Hastings
    0.06
     notation
    0.06
    Activations Density 0.057%

    No Known Activations