© 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. 59204
    Prev
    Next
    INDEX
    Explanations

    words related to exceeding or outdoing benchmarks or records

    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
    zac
    -0.07
    zia
    -0.07
    ashes
    -0.07
    tober
    -0.06
    عÙĪد
    -0.06
    isp
    -0.06
    atsu
    -0.06
     Uhr
    -0.06
    obi
    -0.06
    isu
    -0.06
    POSITIVE LOGITS
    ively
    0.12
    ingly
    0.11
    es
    0.09
    nger
    0.09
    iche
    0.07
    sing
    0.07
    ably
    0.07
    ment
    0.07
     ØŃاج
    0.07
    enger
    0.07
    Activations Density 0.004%

    No Known Activations