© 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 EvalsExportsAPI 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. 55992
    Prev
    Next
    INDEX
    Explanations

    structured code snippets and programming-related constructs

    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
    ÑĦÑĸ
    -0.07
    avery
    -0.07
    iger
    -0.07
    ucha
    -0.07
    ëĬĺ
    -0.07
    flt
    -0.07
    ãĢħ
    -0.06
    olk
    -0.06
     certs
    -0.06
    tn
    -0.06
    POSITIVE LOGITS
     Westbrook
    0.08
    chap
    0.06
    reopen
    0.06
    PFN
    0.06
    obuf
    0.06
    kop
    0.06
    458
    0.06
    дап
    0.06
    iras
    0.06
    reon
    0.06
    Activations Density 0.004%

    No Known Activations