© 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. 120550
    Prev
    Next
    INDEX
    Explanations

    instances of the word "On" followed by dates

    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
    128
    -0.07
    enger
    -0.07
    curring
    -0.06
    âĨ
    -0.06
    256
    -0.06
    [sizeof
    -0.06
    _BS
    -0.06
    ÑĢÑĥн
    -0.06
    lasses
    -0.06
    .Feature
    -0.06
    POSITIVE LOGITS
    orda
    0.08
    -urlencoded
    0.07
    symbols
    0.07
    ctal
    0.06
    ecd
    0.06
    izik
    0.06
    anda
    0.06
    iano
    0.06
    TRS
    0.06
     же
    0.06
    Activations Density 0.019%

    No Known Activations