© 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. 104922
    Prev
    Next
    INDEX
    Explanations

    references to materials and their processing, particularly in relation to insulation and packaging

    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
    ALLEL
    -0.07
    ÑĥÑģк
    -0.07
     Bradley
    -0.07
    efs
    -0.07
     Sr
    -0.06
    623
    -0.06
    íĺķ
    -0.06
    785
    -0.06
     welded
    -0.06
    ÑĥÑĩ
    -0.06
    POSITIVE LOGITS
     padding
    0.12
     cushion
    0.12
     layer
    0.11
     Cush
    0.11
     thick
    0.10
     layers
    0.09
    padding
    0.09
     Pad
    0.09
    å±Ĥ
    0.09
     pad
    0.09
    Activations Density 0.063%

    No Known Activations