© 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 EvalsExportsinterp-engineNEWAPI 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. 42428
    Prev
    Next
    INDEX
    Explanations

    technical terms and phrases related to software libraries and programming

    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
    師
    -0.08
     Fallen
    -0.07
    LTR
    -0.07
    templ
    -0.07
     Shields
    -0.07
    ascus
    -0.06
     validationResult
    -0.06
    plaintext
    -0.06
    antine
    -0.06
    ÃľRK
    -0.06
    POSITIVE LOGITS
     loaded
    0.08
     Loading
    0.08
    .loaded
    0.07
     loading
    0.07
     library
    0.07
    iger
    0.07
     Loaded
    0.07
    _loaded
    0.07
     DLL
    0.07
    library
    0.07
    Activations Density 0.029%

    No Known Activations