© 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. 77719
    Prev
    Next
    INDEX
    Explanations

    significant numerical or statistical values in the text

    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
    #echo
    -0.08
    Ìģ
    -0.07
     catalogs
    -0.07
    eln
    -0.07
    ÌĪ
    -0.06
    AML
    -0.06
    ilian
    -0.06
    onium
    -0.06
     behaviors
    -0.06
     nonprofits
    -0.06
    POSITIVE LOGITS
    theid
    0.07
    tainment
    0.07
    ospace
    0.07
    frica
    0.06
    åĭ
    0.06
    `;
    0.06
    rsa
    0.06
    atile
    0.06
     Lotto
    0.06
     sala
    0.06
    Activations Density 0.000%

    No Known Activations