© 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. 86111
    Prev
    Next
    INDEX
    Explanations

    phrases indicating advantages or benefits

    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
    /or
    -0.07
    zin
    -0.07
    еÑĢÑĪ
    -0.07
    iciel
    -0.07
    meaning
    -0.07
    znám
    -0.07
    umes
    -0.06
    ÑĢиз
    -0.06
    ãĥªãĤ¢
    -0.06
    ACE
    -0.06
    POSITIVE LOGITS
     there
    0.07
    825
    0.06
     po
    0.06
     if
    0.06
     that
    0.06
     NotSupportedException
    0.06
     respectively
    0.06
     prest
    0.06
    .echo
    0.06
    isbury
    0.06
    Activations Density 0.019%

    No Known Activations