© 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. 87485
    Prev
    Next
    INDEX
    Explanations

    HTML attribute values in markup code

    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
    otropic
    -0.07
    alog
    -0.07
    imens
    -0.07
    bsub
    -0.06
    ez
    -0.06
    quette
    -0.06
    oton
    -0.06
    Å¡em
    -0.06
    nge
    -0.06
    AuthToken
    -0.06
    POSITIVE LOGITS
    à¹īาà¸ĩ
    0.08
    ëĿ¼ëıĦ
    0.07
    ãĤ©
    0.07
    Enlarge
    0.07
    arten
    0.07
    .getTarget
    0.06
    enheim
    0.06
    forman
    0.06
    ãĥªãĥ¼ãĤº
    0.06
    иденÑĤ
    0.06
    Activations Density 0.000%

    No Known Activations