© 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. 40924
    Prev
    Next
    INDEX
    Explanations

    instances of comparisons or contrasting statements in the text

    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
    usch
    -0.08
    yen
    -0.07
    ilet
    -0.07
    VS
    -0.07
    iffs
    -0.06
    _CSS
    -0.06
    èn
    -0.06
    anik
    -0.06
    oce
    -0.06
    ä¸ĸç´Ģ
    -0.06
    POSITIVE LOGITS
    ä¸Ģä¸ĭ
    0.09
     apples
    0.08
     between
    0.08
     against
    0.07
     two
    0.07
     how
    0.07
     outcomes
    0.07
     iki
    0.07
     междÑĥ
    0.07
    between
    0.07
    Activations Density 0.016%

    No Known Activations