© 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. 106143
    Prev
    Next
    INDEX
    Explanations

    terms related to searching for specific phrases within programming contexts

    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
    anske
    -0.08
    ãĦ
    -0.07
    ardon
    -0.07
     ãĦ
    -0.07
    /embed
    -0.07
    ioni
    -0.07
    ÏĦαν
    -0.07
    azor
    -0.07
    .portal
    -0.07
    ains
    -0.07
    POSITIVE LOGITS
     included
    0.07
     false
    0.06
     INCLUDED
    0.06
     correct
    0.06
    ë¡Ŀ
    0.06
    etect
    0.06
    included
    0.06
     scored
    0.06
     score
    0.06
    mediate
    0.06
    Activations Density 0.055%

    No Known Activations