© 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 EvalsExportsinterp-engineNEWAPI 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. 18016
    Prev
    Next
    INDEX
    Explanations

    occurrences of various forms of the verb "to be"

    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
    å¢
    -0.07
    ufen
    -0.07
    pone
    -0.07
    éĻµ
    -0.07
    intl
    -0.07
    ãĥ¼ãĥķ
    -0.07
    ãĥ¼ãĥ¬
    -0.07
    ấu
    -0.07
     oversight
    -0.07
    xr
    -0.07
    POSITIVE LOGITS
     an
    0.10
     a
    0.10
    ä¸Ģ个
    0.08
     someone
    0.08
     somebody
    0.07
    æĺ¯ä¸Ģ个
    0.07
     himself
    0.06
    ris
    0.06
    a
    0.06
    ock
    0.06
    Activations Density 0.054%

    No Known Activations