© 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. 28798
    Prev
    Next
    INDEX
    Explanations

    words and phrases indicating numerical comparisons or assessments

    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
    EEK
    -0.07
    acco
    -0.07
    linkplain
    -0.07
    etta
    -0.07
    umas
    -0.07
    æģĴ
    -0.07
    afen
    -0.06
    å¹¹ç·ļ
    -0.06
    кав
    -0.06
    令
    -0.06
    POSITIVE LOGITS
     Trab
    0.07
     Era
    0.07
    adius
    0.06
     Germ
    0.06
     centuries
    0.06
    di
    0.06
     Ferr
    0.06
     Bis
    0.06
    553
    0.06
    uration
    0.06
    Activations Density 0.001%

    No Known Activations