© 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. 5-LLAMASCOPE-RES-131K
    11. 125397
    Prev
    Next
    INDEX
    Explanations

    data structures, mathematical equations, and statistical methods

    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
    esta
    -0.06
    apple
    -0.06
    elves
    -0.06
     Klo
    -0.06
     Classified
    -0.06
    út
    -0.06
     interesting
    -0.05
     defa
    -0.05
    cai
    -0.05
    иÑģк
    -0.05
    POSITIVE LOGITS
    usch
    0.07
    .define
    0.07
    ugo
    0.07
    ̣
    0.07
    \xa
    0.06
    ReuseIdentifier
    0.06
    nnen
    0.06
     ArgumentOutOfRangeException
    0.06
     ÐĹав
    0.06
    -placeholder
    0.06
    Activations Density 0.221%

    No Known Activations