© 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. 126590
    Prev
    Next
    INDEX
    Explanations

    negative statements and the concept of impossibility

    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
    âĢ¦)↵↵
    -0.08
    allon
    -0.08
    umd
    -0.08
    ransition
    -0.07
    ="__
    -0.07
    _mC
    -0.07
    æ®Ĭ
    -0.07
    à¸Ļวà¸Ļ
    -0.07
    nung
    -0.07
    код
    -0.07
    POSITIVE LOGITS
     fail
    0.07
     deny
    0.06
     harm
    0.06
     fails
    0.06
     miss
    0.06
     Cotton
    0.06
     ignore
    0.06
     down
    0.06
     not
    0.06
     question
    0.06
    Activations Density 0.027%

    No Known Activations