© 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. 106593
    Prev
    Next
    INDEX
    Explanations

    structured data types and fields 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
    dden
    -0.07
    REV
    -0.07
    edar
    -0.07
    бов
    -0.07
    redd
    -0.07
    uber
    -0.06
    arger
    -0.06
    pered
    -0.06
    島
    -0.06
    oard
    -0.06
    POSITIVE LOGITS
     nonatomic
    0.06
    itect
    0.06
    enna
    0.06
     since
    0.06
    ¶ģ
    0.06
    uss
    0.06
    iker
    0.06
    igmat
    0.06
     Cruc
    0.05
     Latter
    0.05
    Activations Density 0.001%

    No Known Activations