© 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. 86675
    Prev
    Next
    INDEX
    Explanations

    articles and determiners within sentences

    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
    posal
    -0.06
    _pb
    -0.06
     bigger
    -0.06
    linky
    -0.06
    irsch
    -0.06
    Heading
    -0.06
    vý
    -0.06
    仿
    -0.06
    itz
    -0.05
    ULD
    -0.05
    POSITIVE LOGITS
     range
    0.10
     number
    0.10
     array
    0.09
     ton
    0.08
    range
    0.08
    number
    0.07
    (range
    0.07
     alphabet
    0.07
    esa
    0.07
    ixe
    0.07
    Activations Density 0.064%

    No Known Activations