© 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. 42386
    Prev
    Next
    INDEX
    Explanations

    references to specific dates and times throughout the text

    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
    elman
    -0.08
    _putstr
    -0.07
    chal
    -0.07
    macros
    -0.07
    oppers
    -0.07
    ANTE
    -0.07
    arence
    -0.07
    oho
    -0.07
    oks
    -0.07
    TextEdit
    -0.07
    POSITIVE LOGITS
    201
    0.18
    202
    0.14
    200
    0.13
    199
    0.12
    ä»Ĭå¹´
    0.11
    198
    0.10
    197
    0.10
     nÄĥm
    0.09
    196
    0.09
     annually
    0.08
    Activations Density 0.051%

    No Known Activations