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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125473
    Prev
    Next
    INDEX
    Explanations

    references to durability or long-lasting attributes

    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
    arend
    -0.07
    šti
    -0.06
    ìĸij
    -0.06
    eters
    -0.06
    eson
    -0.06
    eter
    -0.06
     @}
    -0.06
    SSION
    -0.06
     cool
    -0.06
    gio
    -0.06
    POSITIVE LOGITS
    Coder
    0.07
    ussen
    0.07
    ango
    0.06
    idata
    0.06
    chein
    0.06
    ÑĸÑģÑĤÑĮ
    0.06
    ssel
    0.06
    agan
    0.06
    him
    0.06
    (strpos
    0.06
    Activations Density 0.007%

    No Known Activations