© 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. 77699
    Prev
    Next
    INDEX
    Explanations

    references to programming practices and code implementations

    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
     automát
    -0.08
    automatic
    -0.08
    iaux
    -0.07
     automatic
    -0.07
    merce
    -0.07
    loi
    -0.07
    Automatic
    -0.07
    -automatic
    -0.07
    atus
    -0.07
    ÑĥÑĢи
    -0.07
    POSITIVE LOGITS
     manual
    0.15
     manually
    0.15
     Manual
    0.12
    manual
    0.11
    Manual
    0.11
     MANUAL
    0.10
     directly
    0.09
    _manual
    0.09
     direct
    0.08
     plain
    0.08
    Activations Density 0.027%

    No Known Activations