© 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. 92013
    Prev
    Next
    INDEX
    Explanations

    instances of the verb "went" in various forms and 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
    vard
    -0.08
    idon
    -0.07
    leen
    -0.07
    udad
    -0.07
    ãģĦãĤĭ
    -0.07
    ardin
    -0.07
    ÑĹ
    -0.07
    opard
    -0.07
    ongan
    -0.07
    idth
    -0.07
    POSITIVE LOGITS
    fir
    0.07
     crossorigin
    0.06
    oxic
    0.06
    etr
    0.06
    oods
    0.06
    rede
    0.06
    /current
    0.06
    upt
    0.06
    ensch
    0.06
    oldem
    0.06
    Activations Density 0.019%

    No Known Activations