© 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. 85257
    Prev
    Next
    INDEX
    Explanations

    references to skills and training

    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
    nero
    -0.09
    uario
    -0.08
    cy
    -0.08
    ohana
    -0.08
     Äijiá»ĥn
    -0.08
    cle
    -0.07
    uarios
    -0.07
    /release
    -0.07
    loat
    -0.07
    LOAT
    -0.07
    POSITIVE LOGITS
     skills
    0.07
    /tools
    0.07
    /styles
    0.06
    /k
    0.06
     needed
    0.06
     necessary
    0.06
    544
    0.06
    rupt
    0.06
     transfer
    0.06
     impres
    0.05
    Activations Density 0.015%

    No Known Activations