© 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. 73635
    Prev
    Next
    INDEX
    Explanations

    terms related to community programs and support initiatives

    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
    SystemService
    -0.06
    ythe
    -0.06
     Summers
    -0.06
     engineered
    -0.06
    islav
    -0.05
     Ellis
    -0.05
     kings
    -0.05
     pet
    -0.05
    atern
    -0.05
     redirection
    -0.05
    POSITIVE LOGITS
     kit
    0.08
     Kit
    0.08
    Kit
    0.08
    aseline
    0.07
    .LoggerFactory
    0.07
    okit
    0.07
     bidi
    0.07
     embroid
    0.07
     íĻľëıĻ
    0.07
     Giang
    0.07
    Activations Density 0.004%

    No Known Activations