© 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. 5-LLAMASCOPE-RES-131K
    11. 126097
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to advanced theoretical concepts

    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
    ugu
    -0.07
     pull
    -0.06
     r
    -0.06
     successor
    -0.06
     or
    -0.05
     weekday
    -0.05
    pull
    -0.05
     recover
    -0.05
     port
    -0.05
     triple
    -0.05
    POSITIVE LOGITS
     dolu
    0.09
    _Unit
    0.08
     vay
    0.08
    unma
    0.08
     célib
    0.08
     semiclass
    0.08
    SPATH
    0.08
    OLON
    0.08
    üz
    0.08
     cih
    0.08
    Activations Density 0.071%

    No Known Activations