© 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. 2648
    Prev
    Next
    INDEX
    Explanations

    references to file formats and conversion processes

    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
    ellen
    -0.06
    bons
    -0.06
    aph
    -0.06
    berger
    -0.06
    onn
    -0.06
     end
    -0.06
    field
    -0.06
    ालय
    -0.06
    OrCreate
    -0.06
    ät
    -0.05
    POSITIVE LOGITS
     formats
    0.09
     Formats
    0.08
    grav
    0.08
     format
    0.07
    Formats
    0.07
    UNK
    0.07
     jeg
    0.07
     formato
    0.07
    IFO
    0.07
    âĢ¦↵↵↵
    0.07
    Activations Density 0.008%

    No Known Activations