© 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. 120575
    Prev
    Next
    INDEX
    Explanations

    terms related to pricing, discounts, and commission structures in a sales context

    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
    gili
    -0.08
    OffsetTable
    -0.08
    etti
    -0.08
    iyim
    -0.07
    ensi
    -0.07
    /of
    -0.07
    mdir
    -0.07
    /rem
    -0.07
    insi
    -0.07
    _marshall
    -0.07
    POSITIVE LOGITS
     precisely
    0.06
     hadn
    0.06
     indeed
    0.06
    only
    0.06
     anyway
    0.06
     only
    0.06
    ilver
    0.06
     test
    0.06
    essler
    0.06
    ComputedStyle
    0.06
    Activations Density 0.011%

    No Known Activations