© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 15-LLAMASCOPE-RES-131K
    6. 61353
    Prev
    Next
    INDEX
    Explanations

    references to popular music and film, particularly incorporating elements of nostalgia

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

    Conjunctions and punctuation that connect related elements in text, particularly in technical contexts like code, documentation, and data structures.

    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
    _GUI
    -0.08
    ijkstra
    -0.07
    /gui
    -0.07
    /apps
    -0.07
    489
    -0.06
    пов
    -0.06
    reet
    -0.06
     Gauge
    -0.06
    .jdesktop
    -0.06
    _gui
    -0.06
    POSITIVE LOGITS
    asy
    0.06
     Schul
    0.06
    asz
    0.06
    Pear
    0.06
    RIES
    0.06
    riere
    0.06
    È
    0.06
     freshwater
    0.05
    .strict
    0.05
     Ful
    0.05
    Activations Density 1.269%

    No Known Activations