© 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. 17060
    Prev
    Next
    INDEX
    Explanations

    references to time periods and changes over time

    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
     unlike
    -0.07
    Unlike
    -0.07
    ocos
    -0.07
     Unlike
    -0.07
     versus
    -0.06
    dera
    -0.06
    ãģĨãģ¡
    -0.06
    avou
    -0.06
     compared
    -0.06
    ooke
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
     nor
    0.07
     Crane
    0.07
    assin
    0.06
    yme
    0.06
    éĤ£ä¹Ī
    0.06
    Ù©
    0.06
     Mich
    0.06
     anymore
    0.06
     simply
    0.06
    Activations Density 0.029%

    No Known Activations