© 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. 105294
    Prev
    Next
    INDEX
    Explanations

    references to exceptional quality in media and performance

    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
     Logical
    -0.06
    ebi
    -0.06
    ByUrl
    -0.06
    mÃŃ
    -0.06
    posables
    -0.06
     typeof
    -0.06
    çīĪ
    -0.06
    ãn
    -0.06
    -builder
    -0.06
    лÑĥг
    -0.06
    POSITIVE LOGITS
     recent
    0.10
    recent
    0.10
     lately
    0.10
    _recent
    0.10
     recently
    0.09
    Recent
    0.09
    ä»Ĭå¹´
    0.08
     Recent
    0.08
     aktuellen
    0.07
    Recently
    0.07
    Activations Density 0.022%

    No Known Activations