© 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. 76825
    Prev
    Next
    INDEX
    Explanations

    terms related to health, medicinal properties, and the effects of natural substances on the body

    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
    sez
    -0.08
    oris
    -0.07
    edException
    -0.07
    atik
    -0.07
    mbH
    -0.07
    alars
    -0.07
    daÅŁ
    -0.07
    ancellationToken
    -0.07
    otec
    -0.07
    celik
    -0.06
    POSITIVE LOGITS
     properties
    0.13
     effects
    0.11
     effect
    0.10
    properties
    0.09
     property
    0.09
     nature
    0.09
     Properties
    0.09
     qualities
    0.09
    Properties
    0.08
     capability
    0.08
    Activations Density 0.013%

    No Known Activations