© 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. 87596
    Prev
    Next
    INDEX
    Explanations

    numerical data related to event counts and statistics

    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
    ima
    -0.07
    agina
    -0.07
    .arm
    -0.07
    eç
    -0.07
    rai
    -0.07
    ÐIJÑĢÑħÑĸв
    -0.07
    pta
    -0.07
    ÅĻÃŃz
    -0.07
    noinspection
    -0.07
    iente
    -0.07
    POSITIVE LOGITS
     average
    0.08
    -average
    0.07
    imli
    0.07
    median
    0.07
     median
    0.06
    average
    0.06
     typically
    0.06
    å¹³åĿĩ
    0.06
     ant
    0.06
     often
    0.06
    Activations Density 0.026%

    No Known Activations