© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 5-LLAMASCOPE-RES-131K
    11. 125435
    Prev
    Next
    INDEX
    Explanations

    content related to electronic or digital products and terminology

    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
    vat
    -0.08
    lew
    -0.07
    estre
    -0.07
    leon
    -0.07
    allas
    -0.07
    vé
    -0.07
    .AddParameter
    -0.07
    Ä°Y
    -0.07
    xit
    -0.07
    chor
    -0.07
    POSITIVE LOGITS
    anzi
    0.06
    uri
    0.06
    atee
    0.06
    URI
    0.06
     grav
    0.05
     SVN
    0.05
    zug
    0.05
     concrete
    0.05
     stamp
    0.05
     MI
    0.05
    Activations Density 0.001%

    No Known Activations