© 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. 85925
    Prev
    Next
    INDEX
    Explanations

    key terms and phrases related to dimensions, awards, and structured data

    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
    hood
    -0.06
    hra
    -0.06
     Wort
    -0.05
    appa
    -0.05
     Morg
    -0.05
    lite
    -0.05
    955
    -0.05
     sim
    -0.05
     McCorm
    -0.05
    .Restr
    -0.05
    POSITIVE LOGITS
    GED
    0.09
    sed
    0.09
    zed
    0.09
    ated
    0.08
    ged
    0.08
    ored
    0.08
    ded
    0.08
    boa
    0.08
    edException
    0.07
    GY
    0.07
    Activations Density 0.157%

    No Known Activations