© 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 EvalsExportsinterp-engineNEWAPI 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. 28043
    Prev
    Next
    INDEX
    Explanations

    proper nouns related to specific people, places, or events

    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
    isher
    -0.07
    elling
    -0.07
    iesta
    -0.07
    éŁ¿
    -0.06
    hon
    -0.06
    sell
    -0.06
    ungan
    -0.06
    Äįel
    -0.06
    ieder
    -0.06
    /GPL
    -0.06
    POSITIVE LOGITS
     Gran
    0.07
    atic
    0.07
    ror
    0.06
    dic
    0.06
    paragus
    0.06
    à¥Ĥà¤Ĥ
    0.06
    oti
    0.06
    dzi
    0.06
    dag
    0.06
    instrument
    0.06
    Activations Density 0.028%

    No Known Activations