© 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. 75155
    Prev
    Next
    INDEX
    Explanations

    concepts related to climate change and its 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
    AtA
    -0.09
    tega
    -0.07
    ãĤªãĥ³
    -0.06
    phere
    -0.06
    cstdint
    -0.06
    wie
    -0.06
    stdClass
    -0.06
    essler
    -0.06
    ninger
    -0.06
    ecera
    -0.06
    POSITIVE LOGITS
     scenario
    0.18
     scenarios
    0.17
     Scenario
    0.16
    Scenario
    0.15
    scenario
    0.15
    _scenario
    0.12
    enarios
    0.08
     simulation
    0.08
     assumptions
    0.08
     model
    0.07
    Activations Density 0.018%

    No Known Activations