© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 89070
    Prev
    Next
    INDEX
    Explanations

    present tense and 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
    ázev
    -0.09
    adients
    -0.08
    ursal
    -0.07
    .SizeF
    -0.07
    actionDate
    -0.07
     addCriterion
    -0.07
    .addComponent
    -0.07
    ManagerInterface
    -0.07
    _Tis
    -0.07
    ControlItem
    -0.07
    POSITIVE LOGITS
    let
    0.06
    gers
    0.06
    etto
    0.06
    erno
    0.06
       
    0.06
     transform
    0.06
    bole
    0.05
     Gund
    0.05
     Bast
    0.05
     boost
    0.05
    Activations Density 0.045%

    No Known Activations