© 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. 17-LLAMASCOPE-RES-131K
    11. 129554
    Prev
    Next
    INDEX
    Explanations

    key transition words and phrases that indicate a change in thought or perspective

    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
    Ìģ
    -0.07
    589
    -0.06
    QueryParam
    -0.06
    úb
    -0.06
    lobals
    -0.06
    ilde
    -0.06
    elman
    -0.06
    826
    -0.06
     bát
    -0.06
    terminate
    -0.06
    POSITIVE LOGITS
    yt
    0.07
    çĤī
    0.06
    á»į
    0.06
    _border
    0.06
    oti
    0.06
    éĤ£ç§į
    0.06
     eh
    0.06
    /documentation
    0.06
    elly
    0.06
     Neu
    0.06
    Activations Density 0.000%

    No Known Activations