© 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. 15-LLAMASCOPE-RES-131K
    11. 88618
    Prev
    Next
    INDEX
    Explanations

    mentions of movies and viewing experiences

    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
     newsp
    -0.06
     Lazar
    -0.05
     Manifest
    -0.05
     Hou
    -0.05
    _preferences
    -0.05
     Dot
    -0.05
     Fake
    -0.05
    azi
    -0.05
     fro
    -0.05
    .Next
    -0.05
    POSITIVE LOGITS
    inus
    0.09
    Deploy
    0.08
    MITTED
    0.07
    оказ
    0.07
    ìĭľëĬĶ
    0.07
    dup
    0.07
    åĢį
    0.07
    Ĥ¤
    0.07
    lease
    0.06
    decorators
    0.06
    Activations Density 0.020%

    No Known Activations