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

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI 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. 127738
    Prev
    Next
    INDEX
    Explanations

    elements related to mathematical calculations and modeling techniques

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

    Scientific/technical abbreviations and specialized terminology used in research contexts, with "NCSM" (likely No-Core Shell Model) appearing most frequently in physics-related documentation.

    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
    uzz
    -0.06
    qs
    -0.06
    tat
    -0.06
    .lua
    -0.06
    iel
    -0.06
     enumerable
    -0.06
    anka
    -0.06
    672
    -0.05
    βε
    -0.05
     universal
    -0.05
    POSITIVE LOGITS
     results
    0.15
    -generated
    0.14
    -produced
    0.13
     output
    0.13
     outputs
    0.12
    çµIJæŀľ
    0.12
     ÑĢезÑĥлÑĮÑĤаÑĤ
    0.12
     result
    0.12
    results
    0.12
    _results
    0.11
    Activations Density 0.231%

    No Known Activations