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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 29634
    Prev
    Next
    INDEX
    Explanations

    structural elements of code comments and documentation

    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
    nie
    -0.06
    iais
    -0.06
    plat
    -0.06
     discrete
    -0.06
    rys
    -0.06
     Flake
    -0.05
    etto
    -0.05
    edis
    -0.05
     range
    -0.05
     mortar
    -0.05
    POSITIVE LOGITS
    Buffer
    0.07
    retty
    0.07
     Buffer
    0.07
     Tmax
    0.07
    complexType
    0.07
     ustanov
    0.07
    heiro
    0.07
    .Physics
    0.07
    cox
    0.07
    aty
    0.07
    Activations Density 0.005%

    No Known Activations