© 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. 4935
    Prev
    Next
    INDEX
    Explanations

    references to statistical data related to demographics and legislation

    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
    ´Ī
    -0.07
    udes
    -0.06
    erial
    -0.06
     land
    -0.06
    erne
    -0.06
     advent
    -0.05
    uyen
    -0.05
    ÃŃ
    -0.05
    -the
    -0.05
     today
    -0.05
    POSITIVE LOGITS
    DataStream
    0.08
    ÑĢÑĸд
    0.07
    ÙĦÙħÙĩ
    0.07
    OOM
    0.07
    .xls
    0.07
    æ£Ĵ
    0.07
    IMER
    0.07
    Surname
    0.07
    Ïİ
    0.07
    íĦ´
    0.07
    Activations Density 0.005%

    No Known Activations