© 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. 92405
    Prev
    Next
    INDEX
    Explanations

    significant phrases or questions related to clarity and understanding in various contexts

    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
    asca
    -0.07
    òi
    -0.06
    .MixedReality
    -0.06
    âĺĨ
    -0.06
    	Copyright
    -0.06
    yonel
    -0.06
    ẩy
    -0.06
    .IsAny
    -0.06
    etik
    -0.06
    OMPI
    -0.05
    POSITIVE LOGITS
     negative
    0.12
    negative
    0.11
     Negative
    0.11
    Negative
    0.10
     negatives
    0.10
    -negative
    0.10
     negativity
    0.09
     absence
    0.08
     neg
    0.08
     NEG
    0.08
    Activations Density 0.028%

    No Known Activations