© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 3117
    Prev
    Next
    INDEX
    Explanations

    references to digital music platforms and related terms

    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
    ÑİÑĢ
    -0.07
    656
    -0.07
    UNET
    -0.07
    amen
    -0.07
    kker
    -0.06
    agate
    -0.06
    ges
    -0.06
    igham
    -0.06
    emaker
    -0.06
    ein
    -0.06
    POSITIVE LOGITS
    .apple
    0.09
    à¸Ħ
    0.08
    ori
    0.07
    illet
    0.07
     Ferd
    0.07
     عÙħ
    0.06
    getter
    0.06
    erate
    0.06
    chemy
    0.06
    rv
    0.06
    Activations Density 0.002%

    No Known Activations