© 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. 15-LLAMASCOPE-RES-131K
    11. 88149
    Prev
    Next
    INDEX
    Explanations

    references to involvement in educational or community organizations

    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
    illions
    -0.11
    æīĢæľī
    -0.10
     Hundreds
    -0.09
     thousands
    -0.09
    ousands
    -0.09
     hundreds
    -0.09
     모ëĵł
    -0.08
    aticon
    -0.08
     Thousands
    -0.08
     many
    -0.08
    POSITIVE LOGITS
     respectively
    0.10
    åĪĨåĪ«
    0.09
    two
    0.09
     two
    0.08
     respective
    0.08
    three
    0.08
     three
    0.07
    -two
    0.07
    different
    0.06
    两个
    0.06
    Activations Density 0.027%

    No Known Activations