© 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. 15-LLAMASCOPE-RES-131K
    11. 88686
    Prev
    Next
    INDEX
    Explanations

    patterns involving numerical data and significant statistics

    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
    ses
    -0.07
    s
    -0.06
    AKE
    -0.06
    iesen
    -0.06
     of
    -0.06
    abil
    -0.06
    ,
    -0.05
     cast
    -0.05
     Cast
    -0.05
    sed
    -0.05
    POSITIVE LOGITS
    orda
    0.08
    yny
    0.08
    ollectors
    0.07
    Å©i
    0.07
     Kaynak
    0.07
    İ
    0.07
    oulos
    0.07
    èĵ
    0.07
    Neal
    0.07
    gba
    0.07
    Activations Density 0.002%

    No Known Activations