© 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. 125675
    Prev
    Next
    INDEX
    Explanations

    instances where information is ambiguous or incomplete

    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
    ÙĤب
    -0.06
    *)_
    -0.06
     Yorker
    -0.06
     capped
    -0.06
    μι
    -0.06
    ัà¸ĩà¸Ļ
    -0.06
    .scalablytyped
    -0.06
     Caps
    -0.06
     Widow
    -0.06
    heart
    -0.05
    POSITIVE LOGITS
     details
    0.08
     spokesman
    0.07
     press
    0.07
     report
    0.07
     information
    0.07
    Details
    0.07
     reporter
    0.07
    ayi
    0.07
     detail
    0.06
    affen
    0.06
    Activations Density 0.015%

    No Known Activations