© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    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. 15-LLAMASCOPE-RES-131K
    11. 113
    Prev
    Next
    INDEX
    Explanations

    punctuation marks, particularly periods and quotation marks, signaling the conclusion or highlighting of statements

    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
    ighbor
    -0.07
    iani
    -0.07
    VO
    -0.07
     ëĭ¤ìļ´ë°Ľê¸°
    -0.07
    ãĥ³ãĥĢ
    -0.07
    .logging
    -0.07
    rvé
    -0.07
    uilder
    -0.07
    Clipboard
    -0.07
    vo
    -0.06
    POSITIVE LOGITS
     thus
    0.07
    ickets
    0.07
     sic
    0.06
    ega
    0.06
     sounds
    0.06
     sog
    0.06
    EGA
    0.06
     Sounds
    0.06
    bows
    0.06
     Thus
    0.05
    Activations Density 0.028%

    No Known Activations