© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 126933
    Prev
    Next
    INDEX
    Explanations

    sequences of numbers, specifically dates or numerical identifiers

    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
     graft
    -0.06
    anza
    -0.06
    oulos
    -0.06
    atik
    -0.06
    ynes
    -0.06
     sci
    -0.06
    rott
    -0.06
     subs
    -0.06
     mat
    -0.06
    018
    -0.05
    POSITIVE LOGITS
    aska
    0.08
    .scalablytyped
    0.07
    PKG
    0.07
    iye
    0.07
    "./
    0.07
     elektrik
    0.07
    ìĿ´íĬ¸
    0.07
    tie
    0.07
    inke
    0.07
    runs
    0.06
    Activations Density 0.000%

    No Known Activations