© 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. 124783
    Prev
    Next
    INDEX
    Explanations

    URLs and links within the text

    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
    lag
    -0.07
    оÑģÑĤÑĥп
    -0.07
    ullet
    -0.07
    ÏĦÏĥ
    -0.07
    oman
    -0.07
    avian
    -0.07
    vyk
    -0.07
    abor
    -0.06
    liner
    -0.06
    ominator
    -0.06
    POSITIVE LOGITS
     Shapiro
    0.07
    AMESPACE
    0.06
    PHPUnit
    0.06
    URNS
    0.06
     Leading
    0.06
    herits
    0.06
    oretical
    0.05
    iry
    0.05
     enrichment
    0.05
     UNU
    0.05
    Activations Density 0.002%

    No Known Activations