© 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. 88294
    Prev
    Next
    INDEX
    Explanations

    expressions and concepts related to improving the world

    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
     Bakan
    -0.07
    olen
    -0.07
    itel
    -0.07
     çµ
    -0.06
    axon
    -0.06
    iju
    -0.06
    orney
    -0.06
    meni
    -0.06
    ocking
    -0.06
    roke
    -0.06
    POSITIVE LOGITS
    928
    0.07
     world
    0.07
    à¹ĥà¸ļ
    0.06
    à¹ĥ
    0.06
    endar
    0.06
    OTTOM
    0.06
    andbox
    0.06
    ilog
    0.06
     upside
    0.06
    546
    0.06
    Activations Density 0.045%

    No Known Activations