© 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. 17-LLAMASCOPE-RES-131K
    11. 74593
    Prev
    Next
    INDEX
    Explanations

    the conjunction "and" in various contexts

    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
    ÄŁinden
    -0.08
    á»ĵn
    -0.07
    atte
    -0.07
    áce
    -0.07
    emailer
    -0.07
    oints
    -0.07
    qtt
    -0.07
    ansı
    -0.06
    ằ
    -0.06
    arking
    -0.06
    POSITIVE LOGITS
    som
    0.06
     %#
    0.06
    /OR
    0.06
    ri
    0.06
    vier
    0.06
    rian
    0.06
    OLF
    0.05
     sup
    0.05
    ean
    0.05
    SEL
    0.05
    Activations Density 0.018%

    No Known Activations