© 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. 79946
    Prev
    Next
    INDEX
    Explanations

    occurrences of the verb "is" along with related forms to indicate existence or state

    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
    eden
    -0.07
    vie
    -0.07
    aska
    -0.07
    ibaba
    -0.07
    duino
    -0.06
    ÇIJ
    -0.06
    аза
    -0.06
    mür
    -0.06
    quals
    -0.06
    /commons
    -0.06
    POSITIVE LOGITS
    BOSE
    0.07
    ahn
    0.07
     Pearl
    0.07
    ignum
    0.06
    alice
    0.06
    pear
    0.06
    URRE
    0.06
    лиÑĤ
    0.06
    าà¸Ĥ
    0.06
    cao
    0.06
    Activations Density 0.018%

    No Known Activations