© 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. 77851
    Prev
    Next
    INDEX
    Explanations

    file extensions and code-related syntax elements

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

    File extension or suffix markers in programming and development contexts, particularly in source code, import statements, and script references.

    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
    mae
    -0.07
    et
    -0.07
    ìļ´ëıĻ
    -0.06
    emu
    -0.06
    -et
    -0.06
     Sadd
    -0.06
    ımızın
    -0.06
    semble
    -0.06
    ERIC
    -0.06
    axe
    -0.06
    POSITIVE LOGITS
    λεκ
    0.06
    iac
    0.06
    avar
    0.06
     conserv
    0.06
     recip
    0.06
    iam
    0.06
    ipi
    0.06
     punch
    0.06
     Punch
    0.06
    iana
    0.05
    Activations Density 0.015%

    No Known Activations