© 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. 77530
    Prev
    Next
    INDEX
    Explanations

    mentions of public comments and requests for information related to environmental or recycling strategies

    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
    kir
    -0.06
    Directory
    -0.06
    ouri
    -0.06
     optarg
    -0.06
    CAPE
    -0.06
    ENDOR
    -0.06
    indo
    -0.06
    ett
    -0.06
    esz
    -0.06
    aram
    -0.06
    POSITIVE LOGITS
     feedback
    0.10
     Feedback
    0.10
    feedback
    0.09
    /input
    0.09
     input
    0.09
    Feedback
    0.09
     Input
    0.08
    å¾ģ
    0.08
     solic
    0.08
     inputs
    0.08
    Activations Density 0.018%

    No Known Activations