© 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. 61456
    Prev
    Next
    INDEX
    Explanations

    phrases indicating contrast or comparison

    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
    eum
    -0.06
    inz
    -0.06
    zim
    -0.06
    sgiving
    -0.06
    ÙĦØ·
    -0.06
    conciliation
    -0.06
    zag
    -0.06
    rette
    -0.06
    ÑĩеÑģ
    -0.06
    .Helper
    -0.06
    POSITIVE LOGITS
    ERO
    0.07
    ÏĮγ
    0.07
     ise
    0.07
    ero
    0.07
    ataires
    0.06
    ancements
    0.06
    indle
    0.06
    سÙĥ
    0.06
    ixe
    0.06
    enco
    0.06
    Activations Density 0.010%

    No Known Activations