© 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. 72163
    Prev
    Next
    INDEX
    Explanations

    variations and instances of language use in different contexts

    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
     ZIP
    -0.06
    اÙĩÙħ
    -0.06
    ëĬIJ
    -0.06
     bull
    -0.06
    lang
    -0.06
     aggreg
    -0.06
    eki
    -0.06
     rival
    -0.06
    .onView
    -0.06
    ROUGH
    -0.06
    POSITIVE LOGITS
    à¹ĭ
    0.07
    ÑģÑıÑĤ
    0.07
     Hindered
    0.07
    Writes
    0.07
    anner
    0.07
    ÑĢавилÑĮ
    0.07
     Kür
    0.07
    _HOT
    0.06
    uez
    0.06
    олÑı
    0.06
    Activations Density 0.001%

    No Known Activations