© 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. 15-LLAMASCOPE-RES-131K
    11. 89556
    Prev
    Next
    INDEX
    Explanations

    references to specific cultural elements or characteristics

    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
     Mag
    -0.06
     uom
    -0.06
    _HOOK
    -0.05
    ampler
    -0.05
    Share
    -0.05
     carc
    -0.05
    adel
    -0.05
    xx
    -0.05
    egral
    -0.05
    åĨĴ
    -0.05
    POSITIVE LOGITS
    $MESS
    0.07
     -----------------------------------------------------------------------------↵
    0.07
    stroy
    0.07
     COPYING
    0.07
     PROGMEM
    0.07
     Huffman
    0.07
    æĸĩåĮĸ
    0.06
    ÑĢоÑĪ
    0.06
    adem
    0.06
     Butterfly
    0.06
    Activations Density 0.003%

    No Known Activations