© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 17-LLAMASCOPE-RES-131K
    11. 82840
    Prev
    Next
    INDEX
    Explanations

    HTML table structures

    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
     landing
    -0.07
     Landing
    -0.07
     nackt
    -0.07
    iveau
    -0.06
    leh
    -0.06
     landed
    -0.06
    owers
    -0.06
    landing
    -0.06
    .catch
    -0.06
    reece
    -0.06
    POSITIVE LOGITS
    oretical
    0.06
    HP
    0.06
    snapshot
    0.06
    artin
    0.06
    IGGER
    0.06
    upp
    0.06
     dynamic
    0.06
    ľ
    0.06
    пов
    0.06
     ri
    0.06
    Activations Density 0.001%

    No Known Activations