© 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 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. 119249
    Prev
    Next
    INDEX
    Explanations

    percentage values and associated statistical expressions

    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
    lett
    -0.09
    ENCHMARK
    -0.08
    UNDLE
    -0.07
     meisten
    -0.07
    Ãļ
    -0.07
    arp
    -0.07
    ovel
    -0.06
    ues
    -0.06
     Busty
    -0.06
    jÃŃž
    -0.06
    POSITIVE LOGITS
    s
    0.10
    å£°éŁ³
    0.09
    nbsp
    0.08
    ़
    0.08
    Ùĩ
    0.08
    redient
    0.08
    redients
    0.08
    wner
    0.08
    ãģĹãĤĩãģĨ
    0.07
    sak
    0.07
    Activations Density 0.137%

    No Known Activations