© 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. 84809
    Prev
    Next
    INDEX
    Explanations

    references to legal or academic institutions and events

    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
    ĵåIJį
    -0.08
    aspers
    -0.07
    inda
    -0.07
    iyim
    -0.07
    abr
    -0.07
    uman
    -0.07
     scaleX
    -0.06
    ÐIJÑĢÑħÑĸв
    -0.06
    ampie
    -0.06
    aley
    -0.06
    POSITIVE LOGITS
    .LayoutStyle
    0.06
     Jah
    0.06
    INCT
    0.06
    odd
    0.05
    rens
    0.05
     econom
    0.05
    §
    0.05
    (ierr
    0.05
    forth
    0.05
    854
    0.05
    Activations Density 0.638%

    No Known Activations