© 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. 60956
    Prev
    Next
    INDEX
    Explanations

    phrases related to certainty and assertion in arguments or statements

    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
    anco
    -0.07
    taire
    -0.07
    enco
    -0.07
    ymi
    -0.07
    ccione
    -0.07
    ixon
    -0.06
    åª
    -0.06
    Byte
    -0.06
    emark
    -0.06
    &type
    -0.06
    POSITIVE LOGITS
     hereby
    0.07
    istrovstvÃŃ
    0.06
     actually
    0.06
    ayscale
    0.06
    utow
    0.06
    astos
    0.06
    Slides
    0.06
     again
    0.06
     here
    0.06
     gonna
    0.06
    Activations Density 0.002%

    No Known Activations