© 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. 103113
    Prev
    Next
    INDEX
    Explanations

    references to specific countries, historical events, and 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
    859
    -0.06
     recurs
    -0.06
     Vict
    -0.06
     ellipt
    -0.06
    mgr
    -0.06
    ument
    -0.06
    edor
    -0.06
    pt
    -0.06
    ardi
    -0.06
    cntl
    -0.05
    POSITIVE LOGITS
    kud
    0.07
    landa
    0.07
     Gerard
    0.07
    abay
    0.07
     доÑĤ
    0.06
    ICC
    0.06
    -No
    0.06
    NECT
    0.06
    Integral
    0.06
    -striped
    0.06
    Activations Density 0.067%

    No Known Activations