© 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. 56195
    Prev
    Next
    INDEX
    Explanations

    code structure and definitions related to classes and fields in programming

    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
     harms
    -0.06
    erno
    -0.06
    ichten
    -0.06
     acquitted
    -0.05
    ern
    -0.05
    473
    -0.05
     cumulative
    -0.05
     acqu
    -0.05
    bubble
    -0.05
    ral
    -0.05
    POSITIVE LOGITS
    BitFields
    0.09
    .mdl
    0.08
    chema
    0.07
    BuilderFactory
    0.07
    ↵↵
    0.07
    iros
    0.07
    _MetaData
    0.07
    ermann
    0.07
    schema
    0.07
    üstü
    0.07
    Activations Density 0.010%

    No Known Activations