© 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. 106494
    Prev
    Next
    INDEX
    Explanations

    numerical or statistical data, particularly related to measurements or counts

    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
    ÅĻev
    -0.08
    .scalablytyped
    -0.07
    viso
    -0.07
    @dynamic
    -0.07
    itest
    -0.07
    èĨ
    -0.07
     venez
    -0.07
    rimon
    -0.06
    /Dk
    -0.06
    ικÏĮÏĤ
    -0.06
    POSITIVE LOGITS
    ije
    0.07
    ADS
    0.06
    igure
    0.06
     Dup
    0.06
    oble
    0.06
    ignet
    0.06
    agal
    0.06
    igy
    0.06
     Bid
    0.06
    illis
    0.06
    Activations Density 0.001%

    No Known Activations