© 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. 85406
    Prev
    Next
    INDEX
    Explanations

    topics relating to discussions or mentions of specific subjects

    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
     actionTypes
    -0.07
    ãĥ§
    -0.07
     Ùĩد
    -0.07
    ÅĻi
    -0.07
    _gem
    -0.07
    raf
    -0.07
    ?>>
    -0.07
    ichni
    -0.06
    .mit
    -0.06
    δή
    -0.06
    POSITIVE LOGITS
     this
    0.09
    this
    0.07
     questo
    0.06
     stuff
    0.06
     diesem
    0.06
    .this
    0.06
    ssl
    0.06
    ,this
    0.06
    (this
    0.05
    ungan
    0.05
    Activations Density 0.042%

    No Known Activations