© 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. 29808
    Prev
    Next
    INDEX
    Explanations

    references to collective ownership or associated groups

    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
    eva
    -0.07
    erp
    -0.06
    ron
    -0.06
     mandate
    -0.06
    obe
    -0.06
    isco
    -0.06
    enheim
    -0.06
    iors
    -0.06
    éĿ
    -0.06
    rons
    -0.06
    POSITIVE LOGITS
    unei
    0.08
     Bowman
    0.08
    subtype
    0.07
    istrovstvÃŃ
    0.07
    ihan
    0.07
     country
    0.07
     system
    0.07
    uales
    0.07
    .pm
    0.07
    owitz
    0.07
    Activations Density 0.029%

    No Known Activations