© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 352
    Prev
    Next
    INDEX
    Explanations

    terms related to financial assistance or forgiveness programs

    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
    iner
    -0.07
    agne
    -0.07
    inq
    -0.06
    inge
    -0.06
    ead
    -0.06
    ilver
    -0.06
     Court
    -0.06
    .boolean
    -0.06
    wie
    -0.06
    kea
    -0.06
    POSITIVE LOGITS
    asename
    0.08
    ongyang
    0.07
    İ
    0.07
    \TestCase
    0.06
    ë°ĶìĿ´
    0.06
    ÑĥÑģка
    0.06
    okens
    0.06
     hous
    0.06
    /*/
    0.06
    reesome
    0.06
    Activations Density 0.050%

    No Known Activations