© 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. 130426
    Prev
    Next
    INDEX
    Explanations

    Boolean values indicating the status or state of operations, particularly focusing on false conditions

    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
    lo
    -0.09
    lot
    -0.08
    sov
    -0.08
    WEEN
    -0.08
    lore
    -0.08
    _UNUSED
    -0.07
    lon
    -0.07
    ilon
    -0.07
    lia
    -0.07
    ized
    -0.07
    POSITIVE LOGITS
    /null
    0.09
    /no
    0.08
    y
    0.08
    /false
    0.07
    enberg
    0.07
    itzer
    0.07
     Keller
    0.06
    771
    0.06
    o
    0.06
    870
    0.06
    Activations Density 0.013%

    No Known Activations