© 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. 15-LLAMASCOPE-RES-131K
    11. 89555
    Prev
    Next
    INDEX
    Explanations

    discussion of themes related to interpretation and emotional depth in storytelling

    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
    ål
    -0.07
    ungal
    -0.06
    abble
    -0.06
    á»įc
    -0.06
    ibal
    -0.06
    kea
    -0.06
     specifier
    -0.06
    né
    -0.06
    utura
    -0.06
    rk
    -0.06
    POSITIVE LOGITS
    mlink
    0.08
     topic
    0.08
    Topic
    0.08
     subject
    0.07
    oute
    0.07
    topic
    0.07
     пÑĢедмеÑĤ
    0.06
    ContentAlignment
    0.06
    046
    0.06
    udur
    0.06
    Activations Density 0.028%

    No Known Activations