© 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. 93906
    Prev
    Next
    INDEX
    Explanations

    technical terminology related to data processing and analysis

    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
    za
    -0.06
    äºĴ
    -0.06
    TextNode
    -0.06
    èŃ·
    -0.06
    773
    -0.06
    vä
    -0.06
     occasional
    -0.05
    .shtml
    -0.05
    izard
    -0.05
     eldre
    -0.05
    POSITIVE LOGITS
    åħ¨
    0.20
     åħ¨
    0.19
     entire
    0.19
    åħ¨éĥ¨
    0.19
     full
    0.18
     whole
    0.17
     ìłĦì²´
    0.17
     ALL
    0.17
     toÃłn
    0.16
    _ALL
    0.16
    Activations Density 0.156%

    No Known Activations