© 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. 73314
    Prev
    Next
    INDEX
    Explanations

    references to box office performance and movie titles

    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
    .scalablytyped
    -0.09
    ÙĪÙĨØ©
    -0.07
    alc
    -0.07
    ìĨ
    -0.07
     prostitut
    -0.07
    ilar
    -0.07
    ylland
    -0.07
    aversal
    -0.07
     dél
    -0.07
    ìĮ
    -0.06
    POSITIVE LOGITS
     Silence
    0.06
    TECTED
    0.06
    iciary
    0.06
    ánu
    0.06
     Kid
    0.06
    _blob
    0.06
    fat
    0.05
    erce
    0.05
    _RELEASE
    0.05
     analy
    0.05
    Activations Density 0.012%

    No Known Activations