© 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. 17-LLAMASCOPE-RES-131K
    11. 29070
    Prev
    Next
    INDEX
    Explanations

    instances of the word "have" 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
    med
    -0.07
    ifo
    -0.07
     likely
    -0.07
    adu
    -0.07
    oro
    -0.06
    yle
    -0.06
    à¹ģล
    -0.06
    ra
    -0.06
    FM
    -0.06
    nat
    -0.06
    POSITIVE LOGITS
    ’ta
    0.08
    isay
    0.07
     access
    0.07
    rottle
    0.07
     fun
    0.07
    veled
    0.07
    ãĥ³ãĥIJ
    0.07
    ĴĪ
    0.06
    ulton
    0.06
    oop
    0.06
    Activations Density 0.043%

    No Known Activations