© 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. 17-LLAMASCOPE-RES-131K
    6. 118255
    Prev
    Next
    INDEX
    Explanations

    technical terms related to programming and computational geometry

    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
    morgan
    -0.07
    ungan
    -0.07
    outil
    -0.06
    rael
    -0.06
    ापन
    -0.06
    pra
    -0.06
    lland
    -0.06
    subst
    -0.06
    myp
    -0.06
    ouri
    -0.06
    POSITIVE LOGITS
    another
    0.07
    åı¦
    0.07
    esi
    0.07
    åı¦ä¸Ģ
    0.07
     another
    0.06
    others
    0.06
     otro
    0.06
     counterpart
    0.06
     karÅŁÄ±
    0.06
    .TryParse
    0.06
    Activations Density 0.086%

    No Known Activations