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

    Neuronpedia

    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. 77974
    Prev
    Next
    INDEX
    Explanations

    phrases related to the action of breaking or splitting something

    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
    anik
    -0.07
    çŁ¢
    -0.07
    amar
    -0.07
    ãģĵãģĿ
    -0.06
    åŀ
    -0.06
    ovsky
    -0.06
    Ñģок
    -0.06
    itech
    -0.06
    esian
    -0.06
    gend
    -0.06
    POSITIVE LOGITS
    erialize
    0.08
    oller
    0.07
     mysteries
    0.07
    azen
    0.06
     egal
    0.06
    jev
    0.06
     puzzles
    0.06
    olls
    0.06
    /address
    0.06
    ystery
    0.05
    Activations Density 0.004%

    No Known Activations