© 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. 17-LLAMASCOPE-RES-131K
    11. 85889
    Prev
    Next
    INDEX
    Explanations

    instances of the word "change" and its variations

    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
    udas
    -0.08
    endar
    -0.08
    uing
    -0.07
    аÑĢÑĮ
    -0.07
    ilim
    -0.07
    asil
    -0.06
    hol
    -0.06
    ucz
    -0.06
    mand
    -0.06
    uring
    -0.06
    POSITIVE LOGITS
     focus
    0.07
     tack
    0.07
     direction
    0.06
    LOCKS
    0.06
     brut
    0.05
     fundamentally
    0.05
    idian
    0.05
     allegiance
    0.05
    ypi
    0.05
     location
    0.05
    Activations Density 0.015%

    No Known Activations