© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 125144
    Prev
    Next
    INDEX
    Explanations

    proper names, especially of people

    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
    ÃĹ↵↵
    -0.09
    -gnu
    -0.08
    spo
    -0.08
    ?url
    -0.08
    Destructor
    -0.08
    tsky
    -0.07
    alfa
    -0.07
    ncoder
    -0.07
    rade
    -0.07
    ombine
    -0.07
    POSITIVE LOGITS
     which
    0.07
     Thi
    0.07
    ',
    0.06
    ",
    0.06
    ↵
    0.06
     is
    0.06
     Trans
    0.05
    uta
    0.05
    ,"
    0.05
     FOX
    0.05
    Activations Density 0.000%

    No Known Activations