© 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. 22-LLAMASCOPE-RES-131K
    11. 4252
    Prev
    Next
    INDEX
    Explanations

    scientific terms related to environmental changes and their impacts

    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
    _pitch
    -0.07
    Ops
    -0.06
    _ops
    -0.06
    ickerView
    -0.06
    PEC
    -0.06
    جاÙĨ
    -0.06
     ìĬ¤íĥĢ
    -0.06
    еÑĢÑĤ
    -0.06
     helicopt
    -0.06
     Intercept
    -0.06
    POSITIVE LOGITS
     ice
    0.11
     Ice
    0.10
    Ice
    0.08
     meg
    0.08
     mam
    0.08
     Ple
    0.08
     gl
    0.08
    ice
    0.08
     retreat
    0.07
     Cord
    0.07
    Activations Density 0.008%

    No Known Activations