© 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. 17-LLAMASCOPE-RES-131K
    11. 83755
    Prev
    Next
    INDEX
    Explanations

    references to billing and insurance information

    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
     dán
    -0.08
    kaar
    -0.07
    kiem
    -0.07
    vip
    -0.07
    adin
    -0.07
    emale
    -0.07
    oug
    -0.06
    ulu
    -0.06
     geom
    -0.06
    ERE
    -0.06
    POSITIVE LOGITS
    hores
    0.06
     Ladies
    0.06
     kola
    0.06
    "strconv
    0.06
    Å¡ov
    0.06
    abort
    0.06
    CTR
    0.06
     Coco
    0.06
    éĩ
    0.06
    iov
    0.06
    Activations Density 0.003%

    No Known Activations