© 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. 72765
    Prev
    Next
    INDEX
    Explanations

    forms of the verb "to be" and their variations in context

    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
    .waitFor
    -0.07
    ãģĹãģı
    -0.07
    sun
    -0.06
    ,unsigned
    -0.06
    ochen
    -0.06
    ãĤĬãģ¨
    -0.06
    iry
    -0.06
     Sir
    -0.06
    å¦ĥ
    -0.06
    ê°ĢìļĶ
    -0.06
    POSITIVE LOGITS
    coni
    0.08
    avia
    0.07
    ometric
    0.06
    implify
    0.06
    pus
    0.06
    uth
    0.06
    466
    0.06
    ISTA
    0.06
    utterstock
    0.06
    UTH
    0.06
    Activations Density 0.003%

    No Known Activations