© 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. 81827
    Prev
    Next
    INDEX
    Explanations

    phrases related to academic and research achievements

    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
    .nt
    -0.07
    avadoc
    -0.07
     precondition
    -0.06
    normally
    -0.06
    enet
    -0.06
    зÑĭ
    -0.06
     mush
    -0.06
     Leather
    -0.06
    processable
    -0.06
    _physical
    -0.06
    POSITIVE LOGITS
    omics
    0.08
     transl
    0.07
    úsqueda
    0.07
    Ñīи
    0.07
    addir
    0.07
    ädchen
    0.06
    ologic
    0.06
     Research
    0.06
    research
    0.06
    ettings
    0.06
    Activations Density 0.025%

    No Known Activations