© 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. 129277
    Prev
    Next
    INDEX
    Explanations

    punctuation marks and special characters used in technical contexts

    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
    úng
    -0.07
    arent
    -0.07
    ække
    -0.07
    atti
    -0.06
    entiful
    -0.06
    usercontent
    -0.06
    afort
    -0.06
    eniz
    -0.06
    awah
    -0.06
    imity
    -0.06
    POSITIVE LOGITS
    ilda
    0.07
    .RequestBody
    0.06
    Fuse
    0.06
    akan
    0.06
    agn
    0.06
    TestFixture
    0.06
    /catalog
    0.06
    AndWait
    0.06
    ADER
    0.06
    ader
    0.06
    Activations Density 0.001%

    No Known Activations