© 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. 74194
    Prev
    Next
    INDEX
    Explanations

    structured programming elements, particularly involving function calls and their parameters

    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
    iba
    -0.07
    isco
    -0.07
    itchens
    -0.06
    etal
    -0.06
    ieber
    -0.06
    nty
    -0.06
    bcm
    -0.06
    (&(
    -0.06
    &e
    -0.06
    ngle
    -0.06
    POSITIVE LOGITS
    ENCIL
    0.07
     nargs
    0.07
    .HOUR
    0.06
     Bust
    0.06
    ocuk
    0.06
     Cody
    0.06
    ãĤ¯ãĤ»
    0.06
     Ze
    0.06
    ç´
    0.06
    çŃ
    0.06
    Activations Density 0.002%

    No Known Activations