© 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. 9-LLAMASCOPE-RES-131K
    11. 95166
    Prev
    Next
    INDEX
    Explanations

    structured data and configuration settings

    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
    ocl
    -0.07
    ÑģÑĤÑİ
    -0.07
    ifique
    -0.07
    ore
    -0.06
     primaryKey
    -0.06
    ÑĩиÑĤ
    -0.06
    blr
    -0.06
    765
    -0.06
    aign
    -0.06
    igu
    -0.06
    POSITIVE LOGITS
    igr
    0.07
    hek
    0.06
     Nes
    0.06
    à¥Ĥद
    0.06
    ensch
    0.06
    GES
    0.06
    IMUM
    0.06
    ضÙĦ
    0.06
    _ray
    0.05
    .Raise
    0.05
    Activations Density 0.000%

    No Known Activations