© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 54584
    Prev
    Next
    INDEX
    Explanations

    keywords and phrases related to questions and answers in a technical context

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

    Code-related terminology, method calls, and references to technology platforms like Stack Overflow, appearing in programming contexts and web forum discussions.

    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
    ntl
    -0.07
    üml
    -0.07
    amba
    -0.07
    aż
    -0.07
    WebKit
    -0.07
     meis
    -0.07
    ltk
    -0.06
    ilik
    -0.06
    eren
    -0.06
    rana
    -0.06
    POSITIVE LOGITS
     Overflow
    0.09
    Overflow
    0.08
     Stack
    0.08
    å¾½
    0.07
     Kag
    0.07
    answered
    0.07
     Bra
    0.07
     answers
    0.07
     communities
    0.07
     Ask
    0.07
    Activations Density 0.005%

    No Known Activations