© 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. 119552
    Prev
    Next
    INDEX
    Explanations

    references to resource requirements or dependencies in various contexts

    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
    ulp
    -0.07
     Julian
    -0.06
    onical
    -0.06
    ãĥ©ãĤ¹
    -0.06
    é¬
    -0.05
    ault
    -0.05
    .camel
    -0.05
    uly
    -0.05
    iffe
    -0.05
     McKenzie
    -0.05
    POSITIVE LOGITS
     require
    0.24
     requires
    0.23
     Require
    0.21
    require
    0.21
     requiring
    0.21
     requirements
    0.21
     Requires
    0.20
    requires
    0.20
     requirement
    0.20
    Requires
    0.19
    Activations Density 0.101%

    No Known Activations