© 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 EvalsExportsAPI 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. 76513
    Prev
    Next
    INDEX
    Explanations

    phrases indicating quantities or comparisons

    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
    913
    -0.07
    ikon
    -0.06
    tring
    -0.06
    gee
    -0.06
    FIELDS
    -0.06
    nees
    -0.06
    \grid
    -0.06
    ìĭ¬
    -0.06
    sten
    -0.06
     nad
    -0.06
    POSITIVE LOGITS
    ourg
    0.07
    ìļ°ë¦¬
    0.07
    urgence
    0.07
    Uvs
    0.07
    _NOP
    0.06
     DropIndex
    0.06
    reach
    0.06
    setProperty
    0.06
    ounder
    0.06
    menin
    0.06
    Activations Density 0.013%

    No Known Activations