© 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. 105777
    Prev
    Next
    INDEX
    Explanations

    expressions related to transitions or changes in states or conditions

    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
     nues
    -0.08
    omid
    -0.07
    inesis
    -0.07
    Nhap
    -0.07
    declspec
    -0.07
    arella
    -0.07
    ÑģÑĤиÑĩ
    -0.07
    isku
    -0.06
    Äįel
    -0.06
    uled
    -0.06
    POSITIVE LOGITS
     again
    0.11
     afterwards
    0.10
    again
    0.10
     wieder
    0.08
     Again
    0.08
     thereof
    0.08
    Again
    0.08
     lại
    0.08
     later
    0.08
     thereafter
    0.07
    Activations Density 0.047%

    No Known Activations