© 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. 58026
    Prev
    Next
    INDEX
    Explanations

    project-related directories and file paths 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
    isyon
    -0.07
    å¢
    -0.07
    tro
    -0.07
    ponge
    -0.07
    isc
    -0.06
    iaux
    -0.06
    disk
    -0.06
    lemen
    -0.06
    _msgs
    -0.06
    аÐ
    -0.06
    POSITIVE LOGITS
    MAND
    0.06
    коз
    0.06
    enÃŃ
    0.06
    indre
    0.06
    _outer
    0.06
    _vendor
    0.06
    779
    0.06
    ewn
    0.06
    neh
    0.06
    ASHINGTON
    0.06
    Activations Density 0.005%

    No Known Activations