© 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. 42194
    Prev
    Next
    INDEX
    Explanations

    punctuation and specific numerical or formulaic structures within the text

    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
    oley
    -0.09
    pth
    -0.07
    vÄĽd
    -0.07
    ews
    -0.07
    quette
    -0.07
    é¾Ħ
    -0.07
    ony
    -0.06
    ollow
    -0.06
    /loose
    -0.06
    ulen
    -0.06
    POSITIVE LOGITS
    NECT
    0.06
    clude
    0.06
    WithValue
    0.06
    MimeType
    0.06
    assen
    0.06
    å½±
    0.06
     tern
    0.06
    âij¢
    0.05
    iscard
    0.05
    047
    0.05
    Activations Density 0.188%

    No Known Activations