© 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. 4013
    Prev
    Next
    INDEX
    Explanations

    references to "multi" or concepts involving multiple components or layers

    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
    ras
    -0.08
    s
    -0.08
    sen
    -0.08
    pa
    -0.07
    raj
    -0.07
    pin
    -0.07
    sand
    -0.07
    cy
    -0.07
    aim
    -0.07
    obic
    -0.07
    POSITIVE LOGITS
    pliers
    0.09
    /single
    0.09
     sclerosis
    0.09
    .Multi
    0.08
    iple
    0.07
    plx
    0.07
    /int
    0.07
    plier
    0.07
    plies
    0.07
    /m
    0.07
    Activations Density 0.011%

    No Known Activations