© 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. 75455
    Prev
    Next
    INDEX
    Explanations

    numerical values and quantities

    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
     Cher
    -0.06
    wr
    -0.06
    opia
    -0.06
    utsche
    -0.06
    ebin
    -0.06
    quets
    -0.05
     Stem
    -0.05
    æı
    -0.05
    .arraycopy
    -0.05
    l
    -0.05
    POSITIVE LOGITS
    å¼ı
    0.07
    .scalablytyped
    0.07
    prit
    0.07
    leck
    0.07
    remaining
    0.07
    -NLS
    0.07
    acro
    0.07
    $j
    0.07
    à¹Ģà¸ĩ
    0.06
    annel
    0.06
    Activations Density 0.027%

    No Known Activations