© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57644
    Prev
    Next
    INDEX
    Explanations

    cooking instructions and ingredients in recipes

    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
    Tube
    -0.07
    ova
    -0.07
     Strauss
    -0.07
    het
    -0.06
    ognito
    -0.06
    udies
    -0.06
    qml
    -0.06
    usat
    -0.06
    isers
    -0.06
    ÏĦεÏħ
    -0.06
    POSITIVE LOGITS
     actionTypes
    0.07
    reserved
    0.07
    jom
    0.07
    .CO
    0.07
    uhe
    0.06
    agua
    0.06
    ewater
    0.06
    _Target
    0.06
    à¸Ļà¸Ń
    0.06
    éĶĭ
    0.06
    Activations Density 0.065%

    No Known Activations