© 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. 74777
    Prev
    Next
    INDEX
    Explanations

    keywords related to contests and legal disclaimers

    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
    ông
    -0.08
    onden
    -0.08
    addock
    -0.08
    ekil
    -0.07
    edException
    -0.07
    ATTRIBUTE
    -0.07
    eldom
    -0.07
    947
    -0.07
    ohl
    -0.07
    ạc
    -0.07
    POSITIVE LOGITS
     Void
    0.06
     Ih
    0.06
    een
    0.06
    /in
    0.05
    .addNode
    0.05
    ,void
    0.05
    181
    0.05
     residents
    0.05
    ipt
    0.05
     void
    0.05
    Activations Density 0.001%

    No Known Activations