© 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. 29587
    Prev
    Next
    INDEX
    Explanations

    references to cellular and biological alterations affecting behavior and neurotransmitter balance

    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
    woods
    -0.07
    _EXTENSION
    -0.07
     halves
    -0.06
     freshness
    -0.06
    ilet
    -0.06
    _extension
    -0.06
     دÙħ
    -0.06
     mater
    -0.06
    _extensions
    -0.06
    isp
    -0.06
    POSITIVE LOGITS
     shape
    0.08
    IEL
    0.08
     behavior
    0.07
    ноÑĪ
    0.07
     balance
    0.07
     structure
    0.07
     shaped
    0.06
     composition
    0.06
     behaviour
    0.06
     Balance
    0.06
    Activations Density 0.025%

    No Known Activations