© 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 EvalsExportsinterp-engineNEWAPI 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. 38824
    Prev
    Next
    INDEX
    Explanations

    references to API authentication and access controls

    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
    .scalablytyped
    -0.10
    spb
    -0.08
    mtree
    -0.08
    /Branch
    -0.08
    imler
    -0.08
    ezier
    -0.08
    akter
    -0.08
    à¤Łà¤ķ
    -0.08
    -BEGIN
    -0.07
    _equalTo
    -0.07
    POSITIVE LOGITS
     Schmidt
    0.06
    ayo
    0.06
     Dol
    0.05
     nas
    0.05
    Producer
    0.05
     nos
    0.05
     producers
    0.05
    /ns
    0.05
    %s
    0.05
     ve
    0.05
    Activations Density 0.003%

    No Known Activations