© 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. 87276
    Prev
    Next
    INDEX
    Explanations

    structures related to grammar and sentence generation

    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
    ghan
    -0.08
    çĶŁçļĦ
    -0.07
    onto
    -0.07
    odom
    -0.07
    odium
    -0.07
    èĻ
    -0.07
    .undefined
    -0.07
    @student
    -0.07
    SCII
    -0.06
    íĽĪ
    -0.06
    POSITIVE LOGITS
    addtogroup
    0.07
     either
    0.07
     EITHER
    0.06
    RuleContext
    0.06
     bang
    0.06
    ines
    0.06
     dec
    0.06
     DalÅ¡ÃŃ
    0.06
    _scaling
    0.05
     Sne
    0.05
    Activations Density 0.005%

    No Known Activations