© 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. 5667
    Prev
    Next
    INDEX
    Explanations

    themes of change, escape, and the desire for a new life

    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
    itti
    -0.08
    áº
    -0.07
    EMBER
    -0.06
     slog
    -0.06
    onium
    -0.06
     camino
    -0.06
     SharedModule
    -0.06
    clipboard
    -0.06
    arms
    -0.06
    वत
    -0.06
    POSITIVE LOGITS
     escape
    0.18
     away
    0.17
    away
    0.15
     Away
    0.15
    escape
    0.15
    Away
    0.15
     Escape
    0.15
    -away
    0.14
     escaping
    0.14
     escapes
    0.14
    Activations Density 0.060%

    No Known Activations