© 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. 39749
    Prev
    Next
    INDEX
    Explanations

    mathematical notations and structures

    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
    æ³ķ人
    -0.08
    rgan
    -0.07
     sieve
    -0.07
    IMPLEMENT
    -0.07
     fos
    -0.06
    allas
    -0.06
    åĮĹå¸Ĥ
    -0.06
    loor
    -0.06
    _IE
    -0.06
    ImageContext
    -0.06
    POSITIVE LOGITS
    chner
    0.06
    éĢł
    0.06
    nut
    0.06
    _heads
    0.06
     Hammer
    0.05
    overn
    0.05
    %C
    0.05
    éra
    0.05
    vine
    0.05
    QT
    0.05
    Activations Density 0.024%

    No Known Activations