© 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. 93418
    Prev
    Next
    INDEX
    Explanations

    instances of the word "as" indicating comparisons or contexts

    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
    esub
    -0.07
    件äºĭ
    -0.07
     anmeld
    -0.07
    lator
    -0.06
    mond
    -0.06
    mitter
    -0.06
    sie
    -0.06
    cec
    -0.06
    quam
    -0.06
    ãĥ³ãĤ¯
    -0.06
    POSITIVE LOGITS
    arth
    0.07
    ůž
    0.06
    endale
    0.06
    azen
    0.06
    afil
    0.06
     ä½IJ
    0.06
    uncated
    0.06
    aph
    0.05
    éĢĢåĩº
    0.05
    attro
    0.05
    Activations Density 0.020%

    No Known Activations