© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 57498
    Prev
    Next
    INDEX
    Explanations

    scientific terminology related to radio emissions and spectra

    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
     abstract
    -0.07
     immigration
    -0.06
    quat
    -0.06
     ad
    -0.06
     migration
    -0.06
     Abstract
    -0.06
     fault
    -0.06
    adro
    -0.06
     alte
    -0.06
     Fault
    -0.05
    POSITIVE LOGITS
    ýn
    0.09
    Intensity
    0.08
    Bracket
    0.07
    inceton
    0.07
    radi
    0.07
    .fil
    0.07
    -opacity
    0.07
    Directive
    0.07
    ýt
    0.07
    ActivityIndicator
    0.07
    Activations Density 0.039%

    No Known Activations