© 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. 16146
    Prev
    Next
    INDEX
    Explanations

    XML tags and structure in code

    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
    illon
    -0.07
    ngine
    -0.07
    ãĥ¼ãĥĪ
    -0.06
    \<^
    -0.06
    ãĥ¼ãĥ
    -0.06
    landers
    -0.06
    theless
    -0.06
    ajan
    -0.06
    oot
    -0.06
    citation
    -0.06
    POSITIVE LOGITS
    HING
    0.07
    .fp
    0.07
    ItemImage
    0.06
    PackageName
    0.06
    #__
    0.06
    @brief
    0.06
    ICODE
    0.06
    \Context
    0.06
     ”↵↵
    0.06
     Affero
    0.06
    Activations Density 0.051%

    No Known Activations