© 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. 1713
    Prev
    Next
    INDEX
    Explanations

    various forms of the verb "to go" in different contexts

    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
    ampoline
    -0.08
    ly
    -0.07
    enko
    -0.07
    enze
    -0.07
    maid
    -0.07
    quez
    -0.07
    aversal
    -0.07
    /un
    -0.07
    quoi
    -0.07
    mav
    -0.07
    POSITIVE LOGITS
    ÅĤÄħ
    0.08
    364
    0.07
    dart
    0.07
    thic
    0.07
    frey
    0.07
    nings
    0.06
    ipping
    0.06
    adal
    0.06
    erner
    0.06
    adget
    0.06
    Activations Density 0.017%

    No Known Activations