© 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. 130632
    Prev
    Next
    INDEX
    Explanations

    references to specific terms or names associated with design and craftsmanship

    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
    pliers
    -0.08
    raphics
    -0.08
    GLOSS
    -0.08
    makers
    -0.08
    staking
    -0.07
    à¸ģรà¸ĵ
    -0.07
    leur
    -0.07
    à¸ĩาà¸Ļ
    -0.07
    edar
    -0.07
    untas
    -0.07
    POSITIVE LOGITS
    folio
    0.08
    centaje
    0.07
    rait
    0.06
    ollen
    0.06
     clap
    0.06
    celain
    0.06
    folios
    0.06
    ówn
    0.06
     Maurice
    0.06
    rell
    0.05
    Activations Density 0.008%

    No Known Activations