© 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. 54633
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and formatting indicators

    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
    rtl
    -0.07
     frei
    -0.07
    FFE
    -0.07
    _LL
    -0.07
    .addObject
    -0.07
    .setDefault
    -0.07
    rai
    -0.06
    ãģłãģ£ãģ¦
    -0.06
    alytics
    -0.06
    facts
    -0.06
    POSITIVE LOGITS
    ï¸ı
    0.08
    ighbor
    0.06
    .scalablytyped
    0.06
    peed
    0.06
    ly
    0.06
    polator
    0.06
    ellig
    0.06
    ously
    0.06
     Gand
    0.06
    ector
    0.06
    Activations Density 0.001%

    No Known Activations