© 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. 15-LLAMASCOPE-RES-131K
    11. 103244
    Prev
    Next
    INDEX
    Explanations

    details about weights and measurements, particularly in a competitive context

    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
    iddy
    -0.08
    iliz
    -0.08
    .SDK
    -0.07
    xac
    -0.07
    readcr
    -0.07
     expend
    -0.07
    mada
    -0.07
    illow
    -0.06
    ieder
    -0.06
    endir
    -0.06
    POSITIVE LOGITS
     Inn
    0.06
    ëŀĢ
    0.06
    รวม
    0.06
     ëijĺ
    0.05
     Elect
    0.05
    onica
    0.05
     åħ
    0.05
     Serial
    0.05
    plib
    0.05
    mouseenter
    0.05
    Activations Density 0.005%

    No Known Activations