© 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. 61959
    Prev
    Next
    INDEX
    Explanations

    phrases that describe food and its attributes

    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
    idar
    -0.07
    ond
    -0.06
    fd
    -0.06
    ias
    -0.06
    voÅĻÃŃ
    -0.06
     irres
    -0.06
    .Cascade
    -0.06
     sheer
    -0.06
    Tpl
    -0.06
    Ðİ
    -0.05
    POSITIVE LOGITS
     twist
    0.10
     added
    0.09
     hint
    0.09
    avian
    0.08
     underlying
    0.08
     slightly
    0.07
    added
    0.07
     hints
    0.07
    hint
    0.07
     Added
    0.07
    Activations Density 0.014%

    No Known Activations