© 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. 60231
    Prev
    Next
    INDEX
    Explanations

    references to business consultation and community 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
     {}.
    -0.06
    ;
    -0.06
     fian
    -0.06
    ifest
    -0.05
     _______,
    -0.05
    erset
    -0.05
    ãĤ¤ãĥī
    -0.05
    .SendMessage
    -0.05
    xFFFFFF
    -0.05
    ãģĹãģ¦ãģĬãĤĬ
    -0.05
    POSITIVE LOGITS
    ulan
    0.07
    agn
    0.07
     Bale
    0.07
    "nil
    0.06
     ):↵↵
    0.06
    ale
    0.06
    ↵↵
    0.06
    onya
    0.06
    |$
    0.06
    ä»
    0.06
    Activations Density 0.159%

    No Known Activations