© 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. 125616
    Prev
    Next
    INDEX
    Explanations

    references to computer programming and technical commands

    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
    ook
    -0.06
    ((*
    -0.06
     underground
    -0.06
    _define
    -0.05
    Enum
    -0.05
     Seah
    -0.05
    _pb
    -0.05
    irsch
    -0.05
    abbo
    -0.05
    trak
    -0.05
    POSITIVE LOGITS
     vÄĽ
    0.07
    'gc
    0.07
    orts
    0.07
     Spl
    0.06
    build
    0.06
    itizen
    0.06
     IMAGE
    0.06
     Imaging
    0.06
    ÏĦή
    0.06
    اÙĨت
    0.06
    Activations Density 0.008%

    No Known Activations