© 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. 117514
    Prev
    Next
    INDEX
    Explanations

    terms related to software development and programming languages

    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
     Eid
    -0.06
    ressed
    -0.06
    legg
    -0.06
    èĥ
    -0.06
    iele
    -0.06
    ead
    -0.06
    Ðĩ
    -0.06
     Fritz
    -0.06
     laut
    -0.06
     Educational
    -0.06
    POSITIVE LOGITS
     altogether
    0.07
    474
    0.07
    ãĤĪãģĨ
    0.07
    bens
    0.07
     unfamiliar
    0.06
     DISCLAIM
    0.06
     terminology
    0.06
     Alto
    0.06
    apsible
    0.06
    reon
    0.06
    Activations Density 0.011%

    No Known Activations