© 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. 57310
    Prev
    Next
    INDEX
    Explanations

    academic journal articles and their classifications

    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
    225
    -0.06
    archs
    -0.06
     paste
    -0.06
    аков
    -0.05
     copies
    -0.05
     Barth
    -0.05
    age
    -0.05
     g
    -0.05
    夫
    -0.05
     Asi
    -0.05
    POSITIVE LOGITS
     Äįin
    0.08
     addCriterion
    0.08
    SKTOP
    0.07
    ertino
    0.07
    Å¡it
    0.07
    ToFront
    0.07
     odv
    0.07
    ãĥ¼ãĥijãĥ¼
    0.07
    ebilecek
    0.07
    ertiary
    0.07
    Activations Density 0.006%

    No Known Activations