© 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. 84380
    Prev
    Next
    INDEX
    Explanations

    past tense 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
    ÑģÑĤвоÑĢ
    -0.08
    tha
    -0.06
    elmet
    -0.06
    UN
    -0.06
    316
    -0.06
     než
    -0.06
    γά
    -0.06
    γοÏħ
    -0.06
     возÑĢаÑģÑĤ
    -0.06
     degree
    -0.05
    POSITIVE LOGITS
     ones
    0.09
    illac
    0.08
    ết
    0.07
    UPI
    0.07
    rente
    0.07
    cox
    0.07
    breaker
    0.07
     antic
    0.07
    HQ
    0.07
    asca
    0.07
    Activations Density 0.035%

    No Known Activations