© 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. 17-LLAMASCOPE-RES-131K
    11. 125172
    Prev
    Next
    INDEX
    Explanations

    references to specific television shows or series

    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
    yms
    -0.06
    ereum
    -0.06
     Ost
    -0.06
    GLOBALS
    -0.05
     bilateral
    -0.05
    .authenticate
    -0.05
    454
    -0.05
    ipop
    -0.05
    ÑĢоп
    -0.05
    HC
    -0.05
    POSITIVE LOGITS
     anthology
    0.10
     Pilot
    0.09
     anth
    0.08
     pilots
    0.08
     Anth
    0.07
     stories
    0.07
     pilot
    0.07
     shorts
    0.07
    ichert
    0.07
     Stories
    0.07
    Activations Density 0.005%

    No Known Activations