© 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. 15-LLAMASCOPE-RES-131K
    11. 150
    Prev
    Next
    INDEX
    Explanations

    code-related syntax elements, particularly pertaining to function definitions and method calls

    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
    pler
    -0.07
    odb
    -0.07
    ẹ
    -0.07
    AZY
    -0.07
    STYPE
    -0.07
    å¼¥
    -0.06
     Father
    -0.06
    ativ
    -0.06
     accumulator
    -0.06
    ploy
    -0.06
    POSITIVE LOGITS
     equ
    0.07
     hole
    0.06
    oids
    0.06
    375
    0.06
    ear
    0.06
    oki
    0.06
    rors
    0.06
    chner
    0.06
    574
    0.06
    ibur
    0.06
    Activations Density 0.033%

    No Known Activations