© 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. 5-LLAMASCOPE-RES-131K
    11. 126819
    Prev
    Next
    INDEX
    Explanations

    words related to extraordinary events 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
    raç
    -0.07
    swire
    -0.07
    erli
    -0.07
    anken
    -0.07
    kening
    -0.07
    meni
    -0.06
    åij½
    -0.06
    kili
    -0.06
    /Area
    -0.06
    atem
    -0.06
    POSITIVE LOGITS
    ź
    0.06
    avis
    0.06
    0.06
    æĢģ
    0.06
    æ´
    0.06
    sal
    0.06
     Gio
    0.06
    ιÏİν
    0.06
     TRACE
    0.06
    _SHIFT
    0.06
    Activations Density 0.001%

    No Known Activations