© 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. 15-LLAMASCOPE-RES-131K
    11. 86608
    Prev
    Next
    INDEX
    Explanations

    email addresses or contact information

    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
    lich
    -0.07
    usted
    -0.06
    rá
    -0.06
    ught
    -0.06
    elyn
    -0.06
    arem
    -0.06
    ersen
    -0.06
    ings
    -0.06
    rie
    -0.06
    .scalablytyped
    -0.06
    POSITIVE LOGITS
    à¸Ķร
    0.08
    siz
    0.07
    Wnd
    0.06
    Sexy
    0.06
    allo
    0.06
    ginas
    0.06
     Nack
    0.06
    oti
    0.06
     Sexy
    0.06
    leton
    0.06
    Activations Density 0.007%

    No Known Activations