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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 118316
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate community development and investment

    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
    าสà¸ķร
    -0.08
    .Mapping
    -0.08
     geile
    -0.08
    заб
    -0.08
    ContentLoaded
    -0.08
    Scalars
    -0.07
    âu
    -0.07
    梨
    -0.07
    renom
    -0.07
    ptype
    -0.07
    POSITIVE LOGITS
     electricity
    0.07
     base
    0.07
     shovel
    0.06
     available
    0.06
     Site
    0.06
     imm
    0.06
     inherit
    0.06
     availability
    0.06
    åĪ¶
    0.06
    at
    0.06
    Activations Density 0.034%

    No Known Activations