© 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. 39301
    Prev
    Next
    INDEX
    Explanations

    terms related to subscription services

    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
    139
    -0.07
    eger
    -0.07
    /she
    -0.07
    ides
    -0.07
    вÑĸд
    -0.06
    kr
    -0.06
    imm
    -0.06
    sten
    -0.06
    flush
    -0.06
    adh
    -0.06
    POSITIVE LOGITS
    tember
    0.09
    UBLE
    0.08
    =sub
    0.08
     dÄ±ÅŁÄ±
    0.08
    inkle
    0.08
    /Sub
    0.08
    ucus
    0.07
    ption
    0.07
    bable
    0.07
    tsky
    0.07
    Activations Density 0.006%

    No Known Activations