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

    Neuronpedia

    Jacobian LensNEW
    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. 76460
    Prev
    Next
    INDEX
    Explanations

    syntax-related elements in programming code

    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
    ammen
    -0.08
    amoto
    -0.07
    éĺħ读次æķ°
    -0.06
    SOEVER
    -0.06
    ]âĢı
    -0.06
    æĶ¯
    -0.06
    CLAIM
    -0.06
    elli
    -0.06
    件
    -0.06
    @nate
    -0.06
    POSITIVE LOGITS
    ernet
    0.08
     Tribe
    0.07
    anka
    0.07
    serrat
    0.07
    upp
    0.06
    att
    0.06
     MATRIX
    0.06
    slu
    0.06
    iska
    0.06
    ety
    0.06
    Activations Density 0.001%

    No Known Activations