© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 15-LLAMASCOPE-RES-131K
    11. 87971
    Prev
    Next
    INDEX
    Explanations

    the conjunction "of" in various 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
    ationally
    -0.06
    estruct
    -0.06
    lood
    -0.06
    ovation
    -0.06
    hil
    -0.06
    002
    -0.06
    ales
    -0.05
    anja
    -0.05
    ĥĿ
    -0.05
    illis
    -0.05
    POSITIVE LOGITS
    mbH
    0.08
    ansi
    0.07
    onte
    0.07
    (æľĪ
    0.07
    antes
    0.07
    ORED
    0.07
    ãİ
    0.06
    ürnberg
    0.06
    agram
    0.06
    .Face
    0.06
    Activations Density 0.003%

    No Known Activations