© 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. 125163
    Prev
    Next
    INDEX
    Explanations

    programming-related syntax, particularly related to metadata and type definitions in code

    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
    kbd
    -0.06
    PN
    -0.06
     Kahn
    -0.06
     verb
    -0.06
    ureen
    -0.06
    /animations
    -0.06
    egan
    -0.06
    "crypto
    -0.06
    _TestCase
    -0.06
    plex
    -0.06
    POSITIVE LOGITS
    UNT
    0.07
    ãĥĨãĥ«
    0.07
    ednou
    0.06
    ort
    0.06
     Musical
    0.06
    0.06
    سر
    0.06
    .Async
    0.06
    725
    0.06
    _PB
    0.06
    Activations Density 0.002%

    No Known Activations