© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 56958
    Prev
    Next
    INDEX
    Explanations

    anatomical terms and descriptions related to hand joints

    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
     paths
    -0.07
     inside
    -0.07
     Inside
    -0.06
    rok
    -0.06
    paths
    -0.06
     path
    -0.06
    dent
    -0.06
    bone
    -0.06
     domin
    -0.06
     intra
    -0.06
    POSITIVE LOGITS
    æľ«
    0.11
     ends
    0.09
     end
    0.09
    å°¾
    0.09
     Ends
    0.09
    머
    0.08
    TAIL
    0.08
     tail
    0.08
     rear
    0.08
     segment
    0.08
    Activations Density 0.090%

    No Known Activations