© 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. 62255
    Prev
    Next
    INDEX
    Explanations

    terms related to "finishing" or completing tasks and projects

    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
    ker
    -0.07
    upa
    -0.07
    kker
    -0.07
    isan
    -0.07
    loor
    -0.07
    -fashioned
    -0.07
    tie
    -0.07
    unik
    -0.07
    ishly
    -0.07
    indow
    -0.07
    POSITIVE LOGITS
    (es
    0.10
    ãĥ§
    0.09
    er
    0.08
    ãĥ¡ãĥ³ãĥĪ
    0.08
    es
    0.08
    ment
    0.08
    ers
    0.08
    erd
    0.07
    ow
    0.07
    esser
    0.07
    Activations Density 0.017%

    No Known Activations