© 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. 17-LLAMASCOPE-RES-131K
    11. 78198
    Prev
    Next
    INDEX
    Explanations

    references to products or items for sale

    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
     ju
    -0.07
    andal
    -0.06
    ODB
    -0.06
    amel
    -0.06
    äºĮ人
    -0.06
    owed
    -0.06
    ost
    -0.06
    ObjectType
    -0.06
    ãĥ¼ãĥĵ
    -0.06
    åIJij
    -0.06
    POSITIVE LOGITS
    RenderingContext
    0.07
    üle
    0.07
    muz
    0.06
     Cv
    0.06
    baum
    0.06
    kie
    0.06
     darm
    0.06
    dech
    0.06
    Neal
    0.06
     Moder
    0.06
    Activations Density 0.001%

    No Known Activations