© 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. 15-LLAMASCOPE-RES-131K
    11. 89452
    Prev
    Next
    INDEX
    Explanations

    references to specialized scientific terms or classifications

    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
    oor
    -0.06
     åį
    -0.06
    åĢĴ
    -0.06
    VICE
    -0.06
    fore
    -0.06
    audi
    -0.06
     bans
    -0.06
     Lah
    -0.06
    cle
    -0.06
    Incre
    -0.06
    POSITIVE LOGITS
    edly
    0.07
    aroo
    0.07
    acho
    0.06
    lington
    0.06
    ings
    0.06
    lund
    0.06
    askan
    0.06
    ully
    0.06
    è¢
    0.06
    INGS
    0.06
    Activations Density 0.001%

    No Known Activations