© 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. 29200
    Prev
    Next
    INDEX
    Explanations

    references to changes in infrastructure and construction history

    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
    asco
    -0.07
     upcoming
    -0.07
     forthcoming
    -0.06
    ahan
    -0.06
    215
    -0.06
    .impl
    -0.06
    даÑĤ
    -0.05
    .bias
    -0.05
    \Type
    -0.05
    æī¿
    -0.05
    POSITIVE LOGITS
     current
    0.10
     tod
    0.10
    current
    0.10
     present
    0.10
    íĺ
    0.10
    today
    0.09
    -current
    0.09
    çı¾åľ¨
    0.09
    Current
    0.09
     ì§Ģê¸Ī
    0.09
    Activations Density 0.025%

    No Known Activations