© 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. 92042
    Prev
    Next
    INDEX
    Explanations

    words related to searching or seeking something

    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
    keit
    -0.08
    wig
    -0.07
    ections
    -0.06
    amba
    -0.06
    usk
    -0.06
    cela
    -0.06
    kker
    -0.06
    ICAL
    -0.06
    æĪ¸
    -0.06
    ugal
    -0.06
    POSITIVE LOGITS
    ers
    0.08
    lings
    0.07
    stakes
    0.07
    umar
    0.07
    oning
    0.07
    dust
    0.07
    lessly
    0.07
    ered
    0.06
    oÄį
    0.06
    erness
    0.06
    Activations Density 0.008%

    No Known Activations