© 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. 15-LLAMASCOPE-RES-131K
    11. 61990
    Prev
    Next
    INDEX
    Explanations

    keywords related to scientific and technical terminology

    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
    abase
    -0.07
    oston
    -0.06
    oha
    -0.06
    omik
    -0.06
    reon
    -0.06
    esson
    -0.06
    aran
    -0.05
     Universal
    -0.05
    aes
    -0.05
    .Br
    -0.05
    POSITIVE LOGITS
    zig
    0.08
    egr
    0.07
    \Html
    0.07
    znik
    0.07
     MessageBoxButtons
    0.06
    skirts
    0.06
    NullOrEmpty
    0.06
    cko
    0.06
    382
    0.06
    348
    0.06
    Activations Density 0.013%

    No Known Activations