© 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. 119718
    Prev
    Next
    INDEX
    Explanations

    references to the subject and its actions in a narrative context

    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
    irie
    -0.07
     Jennings
    -0.07
    t
    -0.07
    iveau
    -0.07
    ct
    -0.06
    Ñĭй
    -0.06
     Strom
    -0.06
    usra
    -0.06
    nt
    -0.06
     Emblem
    -0.06
    POSITIVE LOGITS
    aviest
    0.08
    zelf
    0.08
    eÄį
    0.08
    gend
    0.08
    -même
    0.07
    agues
    0.07
    ().'/
    0.07
    vendors
    0.07
    elves
    0.07
    /her
    0.07
    Activations Density 0.003%

    No Known Activations