© 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. 5400
    Prev
    Next
    INDEX
    Explanations

    complex mathematical equations and expressions

    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
    mÃŃn
    -0.07
    Regs
    -0.06
    undos
    -0.06
    _TRNS
    -0.06
    .binding
    -0.06
    cisi
    -0.06
    aeper
    -0.06
    ázi
    -0.06
    singular
    -0.06
     maxlen
    -0.06
    POSITIVE LOGITS
    aged
    0.06
    anche
    0.06
    opia
    0.05
    activ
    0.05
    oped
    0.05
    iku
    0.05
     Ess
    0.05
    ernes
    0.05
    urers
    0.05
     Conditional
    0.05
    Activations Density 0.312%

    No Known Activations