© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 3763
    Prev
    Next
    INDEX
    Explanations

    phrases and terms associated with technology and its applications

    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
    Ỽi
    -0.07
     foc
    -0.07
    .Xtra
    -0.07
     ëĭ¤ìļ´ë°Ľê¸°
    -0.06
    ulos
    -0.06
     зави
    -0.06
    oled
    -0.06
    :&
    -0.06
     photograph
    -0.06
    owan
    -0.06
    POSITIVE LOGITS
     pretty
    0.06
     Shades
    0.06
    duino
    0.06
     пÑĢидеÑĤÑģÑı
    0.06
     funct
    0.06
     STRICT
    0.06
     strictly
    0.06
     distributed
    0.06
     Distributed
    0.05
    ÃŁ
    0.05
    Activations Density 0.000%

    No Known Activations