© 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. 15-LLAMASCOPE-RES-131K
    11. 89927
    Prev
    Next
    INDEX
    Explanations

    information regarding methods of installation

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

    Functional text elements in instructional or technical content that provide guidance, explanations, or connections between steps in how-to articles and tutorials.

    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
    imat
    -0.08
    alez
    -0.06
    [,]
    -0.06
    ادÙĩ
    -0.06
    criptor
    -0.06
    hausen
    -0.06
     Branch
    -0.06
    زاÙĨ
    -0.06
    radient
    -0.06
    iday
    -0.06
    POSITIVE LOGITS
     Wid
    0.07
    aters
    0.07
     steps
    0.07
    วà¸Ķ
    0.06
    oni
    0.06
    onium
    0.06
     Steps
    0.06
     stalk
    0.06
     ëĮĢíĸī
    0.06
     dac
    0.06
    Activations Density 0.015%

    No Known Activations