© 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. 106500
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate a conclusion or result

    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
    ãĤ¥
    -0.07
    تÙģ
    -0.07
    몬
    -0.07
     Handy
    -0.07
    Ø´ÙħاÙĦÛĮ
    -0.07
    ect
    -0.07
    ÑĢож
    -0.07
    ÑĢей
    -0.07
    _LICENSE
    -0.07
    ï¼Ĭ
    -0.07
    POSITIVE LOGITS
    forth
    0.11
    aneously
    0.08
    mente
    0.08
    ly
    0.07
    antly
    0.07
    ä¹İ
    0.07
    ingly
    0.06
    hin
    0.06
    emente
    0.06
    ily
    0.06
    Activations Density 0.004%

    No Known Activations