© 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. 85475
    Prev
    Next
    INDEX
    Explanations

    phrases indicating definitions or explanations

    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
    ovi
    -0.08
    egas
    -0.07
    uen
    -0.07
    iran
    -0.07
    tron
    -0.07
    getObject
    -0.07
    ago
    -0.07
    uc
    -0.07
    ez
    -0.07
    inde
    -0.07
    POSITIVE LOGITS
    erville
    0.06
    s
    0.06
    *=*=
    0.06
    à¸ļà¸Ħ
    0.06
    Means
    0.05
    means
    0.05
    sav
    0.05
     Means
    0.05
     [=[
    0.05
    dere
    0.05
    Activations Density 0.009%

    No Known Activations