© 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. 105557
    Prev
    Next
    INDEX
    Explanations

    terms associated with conflicts or disagreements

    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
    apsed
    -0.08
    ÐłÐIJ
    -0.07
    smith
    -0.07
    erce
    -0.07
     kles
    -0.07
    aret
    -0.07
    -Ta
    -0.07
    hua
    -0.07
    orman
    -0.07
    /operators
    -0.07
    POSITIVE LOGITS
    /conf
    0.09
    ably
    0.08
    /question
    0.07
    ively
    0.07
    938
    0.07
    able
    0.07
    Solver
    0.07
    ive
    0.07
    /dis
    0.07
     Resolver
    0.06
    Activations Density 0.006%

    No Known Activations