© 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. 75592
    Prev
    Next
    INDEX
    Explanations

    references to important or notable objects or subjects

    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
    luck
    -0.06
    ex
    -0.06
     true
    -0.05
    cade
    -0.05
    nel
    -0.05
     pattern
    -0.05
    ÑĥÑĢÑģ
    -0.05
     figure
    -0.05
    mong
    -0.05
    ansom
    -0.05
    POSITIVE LOGITS
    ÅŁÄ±
    0.08
    ZO
    0.08
     kinds
    0.08
    eniz
    0.07
    úi
    0.07
     sorts
    0.07
    μιÏĥ
    0.07
    enschaft
    0.07
    ẫ
    0.07
    eder
    0.07
    Activations Density 0.060%

    No Known Activations