© 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. 93053
    Prev
    Next
    INDEX
    Explanations

    references to leaves and nature-related elements

    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
     success
    -0.07
    tit
    -0.06
     haz
    -0.06
     linear
    -0.06
    able
    -0.06
     hol
    -0.06
     eval
    -0.05
    istrov
    -0.05
     delegated
    -0.05
    ilis
    -0.05
    POSITIVE LOGITS
    -shaped
    0.12
    -themed
    0.11
     themed
    0.09
     motif
    0.09
    å½¢
    0.08
    -theme
    0.08
     theme
    0.08
    bud
    0.08
     shape
    0.07
    Theme
    0.07
    Activations Density 0.028%

    No Known Activations