© 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. 117543
    Prev
    Next
    INDEX
    Explanations

    instances of the word 'the' in various 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
    abella
    -0.08
    trap
    -0.08
    سÙĪب
    -0.08
    nap
    -0.08
    liest
    -0.07
    chwitz
    -0.07
    theon
    -0.07
    templ
    -0.07
    serve
    -0.07
    CRET
    -0.07
    POSITIVE LOGITS
    oretical
    0.13
    orie
    0.11
    oret
    0.10
    ories
    0.10
    atre
    0.09
    ft
    0.09
    efore
    0.08
    ore
    0.08
    orem
    0.08
    ological
    0.08
    Activations Density 0.075%

    No Known Activations