© 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. 72237
    Prev
    Next
    INDEX
    Explanations

    aspects related to technical or mathematical formatting in documents

    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
    nat
    -0.07
    ewan
    -0.06
    ebo
    -0.06
    sterol
    -0.06
    urge
    -0.06
    atcher
    -0.06
    azel
    -0.06
    ëł¹
    -0.06
    Ñīи
    -0.06
    _UL
    -0.06
    POSITIVE LOGITS
    MouseButton
    0.07
    ££
    0.07
    irá
    0.07
     corres
    0.07
     corresponding
    0.06
     Karlov
    0.06
     Spawn
    0.06
    IRTH
    0.06
    .bundle
    0.06
    icontrol
    0.06
    Activations Density 0.032%

    No Known Activations