© 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. 83255
    Prev
    Next
    INDEX
    Explanations

    time-related durations and measurements

    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
    eh
    -0.07
    icable
    -0.06
    esses
    -0.06
    tion
    -0.06
    ioc
    -0.06
    ops
    -0.06
    cu
    -0.06
    er
    -0.06
    shelf
    -0.06
    UBE
    -0.05
    POSITIVE LOGITS
    ãĢħ
    0.10
    illions
    0.09
    à¹Ĩ
    0.08
     upon
    0.08
    illum
    0.07
    .bunifuFlatButton
    0.07
    igh
    0.07
    unt
    0.07
    ogany
    0.07
    -long
    0.07
    Activations Density 0.037%

    No Known Activations