© 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. 106273
    Prev
    Next
    INDEX
    Explanations

    questions about personal actions and procedures

    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
    .scalablytyped
    -0.07
    ibel
    -0.06
    855
    -0.06
    liest
    -0.06
     promise
    -0.06
     gros
    -0.06
    oday
    -0.06
    felt
    -0.06
    pon
    -0.06
    forge
    -0.06
    POSITIVE LOGITS
    ее
    0.07
    ysize
    0.07
    ivid
    0.07
    upil
    0.07
    errupted
    0.07
    access
    0.07
     Bones
    0.06
    à¹Ģà¸Ħล
    0.06
    :CGRect
    0.06
    edik
    0.06
    Activations Density 0.006%

    No Known Activations