© 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. 77387
    Prev
    Next
    INDEX
    Explanations

    HTML and programming elements and their associated metadata

    oai_token-act-pair · gpt-4o-miniTriggered by @bot

    Documentation labels or descriptors used in code comments, API references, and configuration files that introduce explanatory text about software components.

    eleuther_acts_top20 · claude-3-7-sonnet-20250219Triggered by @lu-christina
    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
    anta
    -0.07
    ESA
    -0.06
    ίλ
    -0.06
     Bonus
    -0.06
    esa
    -0.06
    imary
    -0.06
     eyeb
    -0.06
     konz
    -0.06
    576
    -0.06
    igen
    -0.05
    POSITIVE LOGITS
     Lorem
    0.08
    @brief
    0.08
     This
    0.08
     description
    0.07
    DOMNode
    0.07
     Description
    0.07
     describes
    0.07
    :description
    0.07
    description
    0.06
    Lorem
    0.06
    Activations Density 0.057%

    No Known Activations