© 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 EvalsExportsinterp-engineNEWAPI 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. 39915
    Prev
    Next
    INDEX
    Explanations

    sections indicating conclusions or summary statements in a 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
    ipo
    -0.07
    دÛĮگر
    -0.07
    quia
    -0.07
    åı¦
    -0.07
    also
    -0.06
    azon
    -0.06
    brook
    -0.06
    åı¦ä¸Ģ
    -0.06
    ibel
    -0.06
    ãĥ¬ãĥĥãĥĪ
    -0.06
    POSITIVE LOGITS
    atten
    0.07
    errick
    0.06
    inar
    0.06
    alore
    0.06
     hereby
    0.06
     Despite
    0.06
    adoo
    0.06
    Ế
    0.06
    cod
    0.06
    erequisite
    0.06
    Activations Density 0.004%

    No Known Activations