© 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. 17-LLAMASCOPE-RES-131K
    6. 77662
    Prev
    Next
    INDEX
    Explanations

    terms related to public documentation and publications

    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
    ingly
    -0.08
    ill
    -0.07
    (es
    -0.07
    alon
    -0.07
    oly
    -0.07
    огод
    -0.06
    mail
    -0.06
    errer
    -0.06
    127
    -0.06
    el
    -0.06
    POSITIVE LOGITS
     "-//
    0.09
    lice
    0.08
    ans
    0.07
    ariat
    0.07
    ally
    0.07
    ären
    0.07
    .publish
    0.06
    itaire
    0.06
    ensex
    0.06
    okrat
    0.06
    Activations Density 0.003%

    No Known Activations