© 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. 15-LLAMASCOPE-RES-131K
    11. 88059
    Prev
    Next
    INDEX
    Explanations

    technical language related to programming functions and object descriptions

    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
     Cursors
    -0.05
     ho
    -0.05
     tet
    -0.05
    ssp
    -0.05
    odd
    -0.05
    ager
    -0.05
     Pros
    -0.05
    _cookie
    -0.05
     wid
    -0.05
    _alias
    -0.05
    POSITIVE LOGITS
    ĶåĽŀ
    0.09
     nackte
    0.07
    uve
    0.07
    avl
    0.07
    arden
    0.07
    VML
    0.07
    egie
    0.07
    arters
    0.07
    oshi
    0.07
    edenÃŃ
    0.07
    Activations Density 0.002%

    No Known Activations