© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 71228
    Prev
    Next
    INDEX
    Explanations

    specific programming functions and method calls in code snippets

    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
    theless
    -0.17
    gether
    -0.15
    plier
    -0.14
    ly
    -0.14
    ity
    -0.14
    istrator
    -0.14
    ive
    -0.13
    thing
    -0.13
    ï¸ı
    -0.13
    Ø©
    -0.13
    POSITIVE LOGITS
    ımın
    0.08
    ing
    0.07
    aad
    0.07
    .setDefault
    0.07
    enen
    0.07
    gger
    0.07
    _unset
    0.06
    à¥įà¤Ľ
    0.06
    teenth
    0.06
    ł
    0.06
    Activations Density 0.161%

    No Known Activations