© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 106025
    Prev
    Next
    INDEX
    Explanations

    terms related to negation or absence

    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
    sworth
    -0.08
    /loose
    -0.07
    ynth
    -0.07
    Specifier
    -0.07
     Goth
    -0.07
    sole
    -0.07
    #undef
    -0.07
    hu
    -0.07
    azzi
    -0.07
    ÏĢά
    -0.07
    POSITIVE LOGITS
     themselves
    0.09
     itself
    0.09
     himself
    0.09
     herself
    0.09
     Himself
    0.07
     ourselves
    0.07
     kendisi
    0.07
     samot
    0.06
    (
    0.06
    èĩªèº«
    0.06
    Activations Density 0.003%

    No Known Activations