© 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. 77953
    Prev
    Next
    INDEX
    Explanations

    themes related to performance and improvement in various contexts

    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
    phis
    -0.08
    ogui
    -0.08
    olie
    -0.08
    ayd
    -0.08
    rame
    -0.08
    rita
    -0.08
    brig
    -0.07
    .getElements
    -0.07
    AGO
    -0.07
    esser
    -0.07
    POSITIVE LOGITS
    835
    0.06
    460
    0.06
     of
    0.06
     across
    0.06
     McKenzie
    0.06
    139
    0.06
    ifs
    0.06
    860
    0.05
     Arrival
    0.05
    cli
    0.05
    Activations Density 0.063%

    No Known Activations