© 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 EvalsExportsAPI 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. 3650
    Prev
    Next
    INDEX
    Explanations

    dates, particularly focusing on the year 1989

    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
    oto
    -0.07
    akat
    -0.07
    resi
    -0.07
    λοÏħ
    -0.07
    lem
    -0.07
    STITUTE
    -0.06
    item
    -0.06
    compan
    -0.06
    ëĵĿ
    -0.06
    û
    -0.06
    POSITIVE LOGITS
    ousel
    0.07
    midt
    0.07
    gnore
    0.06
    ardon
    0.06
    /maps
    0.06
    EO
    0.06
    ibus
    0.06
    asures
    0.06
    è¨Ĥ
    0.06
    »
    0.06
    Activations Density 0.025%

    No Known Activations