© 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. 61103
    Prev
    Next
    INDEX
    Explanations

    instances of the word "document" and its variations, indicating a focus on recording events or 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
    idas
    -0.07
    رÙĤ
    -0.07
    556
    -0.07
    Ñĩин
    -0.07
    ismu
    -0.07
    /apt
    -0.07
    ROL
    -0.06
    stood
    -0.06
    inx
    -0.06
    ivent
    -0.06
    POSITIVE LOGITS
    .scalablytyped
    0.09
    /report
    0.07
     how
    0.07
     progress
    0.07
    222
    0.07
     history
    0.07
     presence
    0.06
     existence
    0.06
    iry
    0.06
    angstrom
    0.06
    Activations Density 0.011%

    No Known Activations