© 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. 9-LLAMASCOPE-RES-131K
    11. 96361
    Prev
    Next
    INDEX
    Explanations

    comparative statements about product quality and features

    oai_token-act-pair · gpt-4o-miniTriggered by @bot
    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
    ounge
    -0.07
    ombat
    -0.07
    atin
    -0.07
    ảnh
    -0.07
    ijk
    -0.06
    ogle
    -0.06
    zee
    -0.06
    ozem
    -0.06
     crossings
    -0.06
    roma
    -0.06
    POSITIVE LOGITS
    grass
    0.07
    528
    0.06
     grass
    0.06
    immel
    0.06
    кид
    0.06
     Grass
    0.06
    -aos
    0.06
    RAY
    0.06
    _configs
    0.06
     RPC
    0.05
    Activations Density 0.028%

    No Known Activations