© 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. 5-LLAMASCOPE-RES-131K
    6. 126686
    Prev
    Next
    INDEX
    Explanations

    terms related to possibilities and appropriateness in various contexts

    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
    phinx
    -0.08
    aji
    -0.08
    ега
    -0.07
    heimer
    -0.07
    uron
    -0.07
    marvin
    -0.07
    elig
    -0.07
    crest
    -0.07
    orman
    -0.07
    avigate
    -0.07
    POSITIVE LOGITS
     brand
    0.06
     fer
    0.06
    ,
    0.06
     alo
    0.06
     Ging
    0.06
     local
    0.06
    enes
    0.06
     tele
    0.06
    indsight
    0.06
     channel
    0.06
    Activations Density 0.003%

    No Known Activations