© 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. 17-LLAMASCOPE-RES-131K
    11. 84704
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming operations and functions

    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
    .scalablytyped
    -0.10
    ëĶĶìĭľ
    -0.08
    ÐIJÑĢÑħÑĸв
    -0.08
    .tbl
    -0.07
    OffsetTable
    -0.07
    ãĨ
    -0.07
     nonatomic
    -0.07
     temin
    -0.07
     <<-
    -0.07
    ëį°ìĿ´íĬ¸
    -0.07
    POSITIVE LOGITS
    orges
    0.07
    Question
    0.07
    ervo
    0.06
    иÑģÑĤÑĢа
    0.06
     Byl
    0.06
    rem
    0.06
    nah
    0.06
    tem
    0.06
    usercontent
    0.06
    ulg
    0.06
    Activations Density 0.170%

    No Known Activations