© 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. 61415
    Prev
    Next
    INDEX
    Explanations

    references to personal experiences and character development in narratives

    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
    LOUR
    -0.06
    翼
    -0.06
    ãĥ©ãĥ³ãĤ¹
    -0.06
    .onViewCreated
    -0.06
    ppe
    -0.06
    eriod
    -0.06
     Rings
    -0.06
    _ic
    -0.06
    loom
    -0.06
    hope
    -0.06
    POSITIVE LOGITS
     forget
    0.11
     forgotten
    0.08
    å¿ĺ
    0.08
     forgot
    0.08
     unnamed
    0.08
     whose
    0.08
     name
    0.08
    whose
    0.07
    rek
    0.07
     Forgot
    0.07
    Activations Density 0.077%

    No Known Activations