© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 85338
    Prev
    Next
    INDEX
    Explanations

    XML namespace declarations

    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
    çŃĨ
    -0.07
    ous
    -0.07
     ÑĢаб
    -0.07
    arsi
    -0.06
    éĽĦ
    -0.06
    idar
    -0.06
    cms
    -0.06
    anson
    -0.06
     Venom
    -0.06
    onet
    -0.06
    POSITIVE LOGITS
    aliyet
    0.06
    LayoutPanel
    0.06
    istrovstvÃŃ
    0.06
     Ferd
    0.06
    ">//
    0.06
     xsi
    0.06
    soever
    0.06
    SupportedContent
    0.06
    áÅĻe
    0.06
    880
    0.06
    Activations Density 0.000%

    No Known Activations