© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 119300
    Prev
    Next
    INDEX
    Explanations

    dates and numerical information related to events

    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
    595
    -0.07
    bilt
    -0.07
    berman
    -0.06
     ÎļÏħ
    -0.06
    utsche
    -0.06
    oyer
    -0.06
    argent
    -0.06
    ayscale
    -0.06
    á»ķi
    -0.06
     âĢı
    -0.06
    POSITIVE LOGITS
    kers
    0.06
     mar
    0.06
    202
    0.06
     konkrét
    0.06
    FFF
    0.06
    ola
    0.06
    isto
    0.06
    COLUMN
    0.06
    ilion
    0.05
     later
    0.05
    Activations Density 0.003%

    No Known Activations