© 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. 62608
    Prev
    Next
    INDEX
    Explanations

    the word "the" as a significant marker in the text

    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
    fty
    -0.08
    alse
    -0.07
    ingen
    -0.07
    PEnd
    -0.07
    FXML
    -0.07
    ÃŃc
    -0.07
    jÃł
    -0.07
     neod
    -0.07
     Ekon
    -0.07
    _PARSE
    -0.06
    POSITIVE LOGITS
     purpose
    0.10
    purpose
    0.09
     aims
    0.09
     aim
    0.08
     purposes
    0.08
    -purpose
    0.07
     objectives
    0.07
    chap
    0.07
    1
    0.07
     present
    0.06
    Activations Density 0.031%

    No Known Activations