© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it
    Neuronpedia
    Jacobian LensNEW
    Natural Language
    Autoencoders
    MAY 26    Assistant AxisJAN 26Circuit TracerAPR 26SteerSAE EvalsExportsinterp-engineNEW Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 98926
    Prev
    Next
    INDEX
    Explanations

    references to specific types of entertainment media

    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
     plays
    -0.06
    ze
    -0.06
    cht
    -0.05
     Las
    -0.05
     rest
    -0.05
    ÙĤر
    -0.05
     disposable
    -0.05
    ither
    -0.05
     REST
    -0.05
     events
    -0.05
    POSITIVE LOGITS
    анка
    0.08
    raki
    0.08
     dopad
    0.08
    Closure
    0.08
    Insets
    0.07
    achuset
    0.07
    رÙĬÙĥÙĬ
    0.07
     flop
    0.07
    éĹŃ
    0.07
    à¤Ŀ
    0.07
    Activations Density 0.018%

    No Known Activations