© 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. 93919
    Prev
    Next
    INDEX
    Explanations

    expressions of personal feelings and opinions

    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
     then
    -0.06
    ibe
    -0.06
    ombres
    -0.06
    oking
    -0.06
     Mixed
    -0.06
     Operating
    -0.06
    uce
    -0.06
     Dudley
    -0.06
    MBOL
    -0.06
     Seek
    -0.05
    POSITIVE LOGITS
    elpers
    0.07
    iglia
    0.07
     doubly
    0.07
    .generated
    0.06
     zwar
    0.06
    olini
    0.06
    stitial
    0.06
    ulin
    0.06
    itin
    0.06
    zure
    0.06
    Activations Density 0.030%

    No Known Activations