© 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 EvalsExportsinterp-engineNEWAPI 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. 62252
    Prev
    Next
    INDEX
    Explanations

    information related to history and cultural 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
    .manage
    -0.07
    arness
    -0.07
    AXB
    -0.07
     khá»ıi
    -0.07
    .MaxLength
    -0.07
    ityEngine
    -0.07
    .subscription
    -0.07
    éĥİ
    -0.07
    ìķ¼
    -0.07
    IColor
    -0.07
    POSITIVE LOGITS
     history
    0.15
     current
    0.12
    history
    0.10
     History
    0.10
     present
    0.10
    current
    0.10
     contemporary
    0.10
    -current
    0.09
    -history
    0.09
    History
    0.09
    Activations Density 0.036%

    No Known Activations