© 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. 14522
    Prev
    Next
    INDEX
    Explanations

    references to news articles or imagery credits

    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
     Verd
    -0.06
    oft
    -0.05
    ople
    -0.05
    yclopedia
    -0.05
    ate
    -0.05
     Impress
    -0.05
    enance
    -0.05
     entity
    -0.05
     established
    -0.05
    oplast
    -0.05
    POSITIVE LOGITS
    UTERS
    0.08
    Composite
    0.07
    Scalars
    0.07
    ضاÙĨ
    0.07
    ãĥªãĥ³
    0.07
    SourceType
    0.07
    å®ħ
    0.07
    è£ģ
    0.07
    .states
    0.07
    APPER
    0.07
    Activations Density 0.012%

    No Known Activations