© 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. 88299
    Prev
    Next
    INDEX
    Explanations

    programming-related terms and conditions

    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
    Ïĥη
    -0.06
     wash
    -0.05
     onBind
    -0.05
    ÑİÑģÑĮ
    -0.05
    cdb
    -0.05
     Rover
    -0.05
     charges
    -0.05
     printk
    -0.05
     powers
    -0.05
    outer
    -0.05
    POSITIVE LOGITS
    ffi
    0.08
     диÑĤи
    0.07
    eya
    0.07
    .UnitTesting
    0.07
    isia
    0.07
    lub
    0.07
    ERG
    0.07
    DRV
    0.07
    itom
    0.07
    lius
    0.07
    Activations Density 0.009%

    No Known Activations