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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87605
    Prev
    Next
    INDEX
    Explanations

    terms related to mathematical or scientific models

    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
    uka
    -0.09
    wich
    -0.07
     exposure
    -0.06
    utton
    -0.06
     exposes
    -0.06
    çuk
    -0.06
     exposures
    -0.06
     ry
    -0.06
    ænd
    -0.06
    ë²Į
    -0.06
    POSITIVE LOGITS
    iban
    0.07
    å¿ł
    0.07
    ISTRIBUT
    0.07
    umlu
    0.06
    ografie
    0.06
    asio
    0.06
    .rdf
    0.06
    agra
    0.06
    Ïģαν
    0.06
    #End
    0.06
    Activations Density 0.000%

    No Known Activations