© 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. 104835
    Prev
    Next
    INDEX
    Explanations

    references to social services and community support

    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
    nil
    -0.07
    ãĤĵãģ©
    -0.07
    bour
    -0.06
     baz
    -0.06
    uent
    -0.06
     Flickr
    -0.06
    ikat
    -0.06
    u
    -0.06
    ÃŃk
    -0.06
     nil
    -0.06
    POSITIVE LOGITS
     our
    0.14
     ours
    0.11
     nostro
    0.10
     nuestro
    0.10
    æĪij们çļĦ
    0.10
     OUR
    0.09
    Our
    0.09
    our
    0.09
     Our
    0.09
     noss
    0.09
    Activations Density 1.202%

    No Known Activations