© 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. 125706
    Prev
    Next
    INDEX
    Explanations

    sentences that contain significant actions or transitions in a narrative context

    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
    hte
    -0.08
    .edu
    -0.07
    lds
    -0.07
    iddy
    -0.07
    undry
    -0.07
    pas
    -0.06
    REA
    -0.06
    .asp
    -0.06
    наÑĤ
    -0.06
    xt
    -0.06
    POSITIVE LOGITS
     meanwhile
    0.07
     then
    0.07
     soon
    0.06
    odos
    0.06
    hoff
    0.06
     while
    0.06
    ONGL
    0.06
    itom
    0.06
    Ãłng
    0.06
    emouth
    0.06
    Activations Density 0.014%

    No Known Activations