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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 27126
    Prev
    Next
    INDEX
    Explanations

    references to construction and development projects

    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
    éri
    -0.06
     Ashton
    -0.06
    astle
    -0.06
     undercut
    -0.06
     embr
    -0.06
    ecast
    -0.06
    ìĿµ
    -0.05
     fres
    -0.05
     clearance
    -0.05
     Listings
    -0.05
    POSITIVE LOGITS
    uler
    0.07
    ittel
    0.07
    iegel
    0.06
     pod
    0.06
    awa
    0.06
    .Submit
    0.06
     moderne
    0.06
     pods
    0.06
    alignment
    0.06
     modern
    0.06
    Activations Density 0.013%

    No Known Activations