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

    Neuronpedia

    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. 16865
    Prev
    Next
    INDEX
    Explanations

    references to frameworks and structures in scientific contexts

    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
    idot
    -0.06
    cow
    -0.06
    vero
    -0.06
    ÏħÏĦÏĮ
    -0.06
    аÑĢаÑĤ
    -0.06
     @}
    -0.06
    SetBranch
    -0.06
    bir
    -0.06
     Cooke
    -0.06
    anes
    -0.06
    POSITIVE LOGITS
    ä½ľä¸º
    0.20
     sebagai
    0.15
     каÑĩеÑģÑĤве
    0.13
     jako
    0.13
     ä½ľ
    0.13
     acting
    0.12
     serving
    0.12
    æĪIJ为
    0.12
     as
    0.12
    æĪIJçĤº
    0.12
    Activations Density 0.109%

    No Known Activations