© 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. 69324
    Prev
    Next
    INDEX
    Explanations

    references to lost objects or remnants associated with a person's identity

    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
    ÑĤаб
    -0.07
    заб
    -0.06
    jedn
    -0.06
     bure
    -0.06
    ɵ
    -0.06
    uteur
    -0.06
     Wheeler
    -0.06
    ÑĢиÑģ
    -0.06
    essian
    -0.06
    /do
    -0.06
    POSITIVE LOGITS
     cockpit
    0.08
    Pieces
    0.07
    amble
    0.07
     Pieces
    0.07
     pieces
    0.07
     recovered
    0.07
    mont
    0.06
     electronic
    0.06
     wreckage
    0.06
    ýn
    0.06
    Activations Density 0.004%

    No Known Activations