© 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. 55824
    Prev
    Next
    INDEX
    Explanations

    questions and statements related to purchasing and quality of 3D printers

    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
     Experimental
    -0.07
    odom
    -0.06
    usable
    -0.06
    :
    -0.06
    Experimental
    -0.06
     Higgins
    -0.06
    ó
    -0.06
    éļİ
    -0.06
    ;
    -0.06
    è³Ģ
    -0.06
    POSITIVE LOGITS
    .operator
    0.07
    software
    0.07
     rugged
    0.07
    capabilities
    0.07
     Jog
    0.07
    äºľ
    0.07
    .lex
    0.07
    /operator
    0.07
    fty
    0.07
     operator
    0.07
    Activations Density 0.002%

    No Known Activations