© 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. 104449
    Prev
    Next
    INDEX
    Explanations

    terms related to non-commercial use

    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
    Ïĥια
    -0.07
     trunc
    -0.06
    sett
    -0.06
    覧
    -0.06
    estate
    -0.06
    ffen
    -0.06
    AttributeName
    -0.06
    Äĥn
    -0.06
     einzel
    -0.06
    Ùıع
    -0.06
    POSITIVE LOGITS
    udas
    0.08
    isque
    0.07
    _FLAGS
    0.07
     vit
    0.06
    ubs
    0.06
    pole
    0.06
    kaar
    0.06
    екÑĤи
    0.06
    æī§
    0.06
    ä»
    0.06
    Activations Density 0.009%

    No Known Activations