© 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. 80774
    Prev
    Next
    INDEX
    Explanations

    references to time travel and its implications

    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
    urum
    -0.08
    upper
    -0.07
    eldom
    -0.07
    obby
    -0.07
    igsaw
    -0.06
    uhe
    -0.06
    μιÏĥ
    -0.06
    errorCode
    -0.06
    çŃĭ
    -0.06
    å¡
    -0.06
    POSITIVE LOGITS
     billions
    0.10
     millions
    0.09
    _alive
    0.07
     alive
    0.07
    illions
    0.07
    utz
    0.07
     somewhere
    0.07
     thousands
    0.07
     earth
    0.07
     trillion
    0.07
    Activations Density 0.040%

    No Known Activations