© 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. 28264
    Prev
    Next
    INDEX
    Explanations

    titles and elements that relate to specific products or items for sale

    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
    erdem
    -0.08
    .fm
    -0.08
    antas
    -0.07
    æ¢ģ
    -0.07
    dojo
    -0.07
     Excell
    -0.07
    åĩ¡
    -0.07
    utedString
    -0.07
    ertools
    -0.07
    _FM
    -0.07
    POSITIVE LOGITS
    ovich
    0.07
    è£ģ
    0.06
     Indoor
    0.06
     Falk
    0.05
    elik
    0.05
     chip
    0.05
    chip
    0.05
     Beacon
    0.05
     Blow
    0.05
     Gry
    0.05
    Activations Density 0.018%

    No Known Activations