© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3905
    Prev
    Next
    INDEX
    Explanations

    instances of the word "first" and related concepts of initial experiences or occurrences

    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
    amat
    -0.07
    ãĥ¼ãĥŃ
    -0.06
    è«ĸ
    -0.06
     amore
    -0.06
    ergy
    -0.06
    ếu
    -0.06
    abil
    -0.06
    esco
    -0.06
    nt
    -0.06
    /device
    -0.06
    POSITIVE LOGITS
     thing
    0.12
     part
    0.09
     question
    0.08
     sentence
    0.07
     thought
    0.07
     Thing
    0.07
    ÑĢиÑĩ
    0.07
    Thing
    0.07
     rule
    0.07
     few
    0.07
    Activations Density 0.037%

    No Known Activations