© 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. 57308
    Prev
    Next
    INDEX
    Explanations

    key elements and plot points related to murder mysteries and crimes

    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
    .cd
    -0.09
    ysi
    -0.08
    intage
    -0.08
    ymm
    -0.08
    .wx
    -0.08
    acher
    -0.08
    .bpm
    -0.08
    éĮĦ
    -0.07
    rame
    -0.07
    ayacak
    -0.07
    POSITIVE LOGITS
     Arabian
    0.06
    458
    0.06
     mon
    0.06
     a
    0.06
     honest
    0.06
     Proud
    0.06
     g
    0.06
    åį
    0.06
     an
    0.06
     b
    0.05
    Activations Density 0.018%

    No Known Activations