© 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 EvalsExportsinterp-engineNEWAPI 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. 73980
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate intent to share information or experiences

    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
    essler
    -0.07
    eldom
    -0.07
    enk
    -0.07
    /Instruction
    -0.07
     mixed
    -0.06
    obel
    -0.06
    aber
    -0.06
     tÆ°á»Łng
    -0.06
    ad
    -0.06
     вÑģпом
    -0.06
    POSITIVE LOGITS
     merely
    0.08
     limitation
    0.07
     coverage
    0.07
     simply
    0.07
    scoped
    0.07
    éĻIJ
    0.07
     scope
    0.07
     limit
    0.07
     Limit
    0.07
     selection
    0.06
    Activations Density 0.024%

    No Known Activations