© 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. 39564
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize existence and stating facts

    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
    .yahoo
    -0.06
    lo
    -0.06
    StackNavigator
    -0.06
    midd
    -0.06
    ossible
    -0.06
    alle
    -0.06
    ;base
    -0.06
    iag
    -0.06
    ема
    -0.06
    eman
    -0.06
    POSITIVE LOGITS
    ÌĨ
    0.09
    plx
    0.08
    页éĿ¢åŃĺæ¡£å¤ĩ份
    0.07
    phans
    0.07
    SplitOptions
    0.07
    Ì
    0.07
    ÌĪ
    0.07
    strap
    0.06
    mlink
    0.06
     Mey
    0.06
    Activations Density 0.295%

    No Known Activations