© 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. 106679
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods

    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
    lear
    -0.07
    -0.07
    inand
    -0.06
    oader
    -0.06
    -UA
    -0.05
    öl
    -0.05
     Sys
    -0.05
    ¶
    -0.05
    lete
    -0.05
     SYS
    -0.05
    POSITIVE LOGITS
     recently
    0.08
     Recently
    0.08
     sometimes
    0.08
     lately
    0.08
     Yet
    0.07
    ÐIJÑĢÑħÑĸв
    0.07
     begs
    0.07
    dden
    0.07
    recent
    0.07
     BUT
    0.07
    Activations Density 0.048%

    No Known Activations