© 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. 17-LLAMASCOPE-RES-131K
    11. 42680
    Prev
    Next
    INDEX
    Explanations

    text related to cinema and its historical context

    oai_token-act-pair · gpt-4o-mini
    Triggered 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
    Negative Logits
    TestCategory
    -0.07
    ibern
    -0.07
    TextNode
    -0.06
    ripp
    -0.06
    моÑĤ
    -0.06
    è¦ĭ
    -0.06
    eniz
    -0.06
    oose
    -0.06
     pl
    -0.06
    _POINTER
    -0.06
    POSITIVE LOGITS
    ans
    0.07
    ensch
    0.06
    ÃŃst
    0.06
    yna
    0.06
    gnore
    0.06
    ANS
    0.06
    arend
    0.06
     Tweets
    0.05
    ignon
    0.05
     quarter
    0.05
    Activations Density 0.005%

    No Known Activations