© 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. 15-LLAMASCOPE-RES-131K
    6. 138
    Prev
    Next
    INDEX
    Explanations

    references to celebrities and their career milestones

    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
    ä¸ģ
    -0.07
    име
    -0.07
    ,...↵↵
    -0.07
    ÅĻe
    -0.07
    urai
    -0.07
    Ìī
    -0.07
    Ù쨱
    -0.07
    dit
    -0.07
    ovÄĽ
    -0.07
    ocations
    -0.06
    POSITIVE LOGITS
    achuset
    0.06
     exert
    0.06
    gota
    0.06
    uther
    0.06
     later
    0.06
    ä¹ĭ
    0.06
    raith
    0.06
    stuff
    0.05
    NoSuch
    0.05
     successfully
    0.05
    Activations Density 0.005%

    No Known Activations