© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 96767
    Prev
    Next
    INDEX
    Explanations

    phrases that denote success and effectiveness in artistic expression

    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
    IDAD
    -0.07
    lices
    -0.07
    úi
    -0.07
     halde
    -0.07
    croft
    -0.07
    ohana
    -0.07
    :host
    -0.06
    ignty
    -0.06
    alon
    -0.06
    iddi
    -0.06
    POSITIVE LOGITS
    StackNavigator
    0.07
    ione
    0.07
     spiral
    0.06
    eto
    0.06
    etur
    0.06
     scale
    0.06
     Jar
    0.06
     balance
    0.06
     m
    0.06
     vir
    0.06
    Activations Density 0.051%

    No Known Activations