© 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. 125254
    Prev
    Next
    INDEX
    Explanations

    references to events, publications, or series along with their associated dates

    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
    ãĥĮ
    -0.08
    ogy
    -0.07
    ALAR
    -0.06
    Ä©
    -0.06
    roup
    -0.06
    _NOTIFY
    -0.06
    /cop
    -0.06
    Tweet
    -0.06
    .GetHashCode
    -0.06
    वर
    -0.06
    POSITIVE LOGITS
     episode
    0.09
     column
    0.08
     Episode
    0.08
    âĦ¢
    0.07
     podcast
    0.07
     episodes
    0.07
     Extra
    0.07
     Column
    0.06
    anik
    0.06
     host
    0.06
    Activations Density 0.029%

    No Known Activations