© 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. 9-LLAMASCOPE-RES-131K
    11. 96745
    Prev
    Next
    INDEX
    Explanations

    predictive phrases or expressions suggesting future events or observations

    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
    ayment
    -0.07
    ignite
    -0.06
     Nachricht
    -0.06
    èĭĹ
    -0.06
    arbon
    -0.06
    ÑĭÑĤ
    -0.06
     financing
    -0.06
    hiba
    -0.05
     fab
    -0.05
    ulk
    -0.05
    POSITIVE LOGITS
    nier
    0.07
    nul
    0.07
    ensburg
    0.07
     Gül
    0.07
    ÛĮÙĨÚ©
    0.07
    翼
    0.07
     Seymour
    0.07
    iku
    0.07
    деÑĢж
    0.07
    رÙģØ©
    0.07
    Activations Density 0.036%

    No Known Activations