© 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. 107467
    Prev
    Next
    INDEX
    Explanations

    references to family-related topics

    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
     g
    -0.07
     e
    -0.06
     leading
    -0.06
     Cont
    -0.06
    -0.06
    át
    -0.06
     Sn
    -0.05
     Z
    -0.05
    essel
    -0.05
     ve
    -0.05
    POSITIVE LOGITS
    opi
    0.08
    emble
    0.08
    .googleapis
    0.08
    etration
    0.08
    egasus
    0.08
    ela
    0.07
    ExecutionContext
    0.07
    echa
    0.07
     libertin
    0.07
    /loose
    0.07
    Activations Density 0.000%

    No Known Activations