© 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. 28077
    Prev
    Next
    INDEX
    Explanations

    titles of songs and films, particularly those that are popular or iconic

    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
    ué
    -0.08
    -0.08
     ↵
    -0.07
    Invariant
    -0.06
    .scalablytyped
    -0.05
    iek
    -0.05
     +
    -0.05
     invariant
    -0.05
    isory
    -0.05
    ogan
    -0.05
    POSITIVE LOGITS
    itzer
    0.09
    (er
    0.08
    aucoup
    0.08
    axes
    0.08
    ERA
    0.07
    eba
    0.07
    çª
    0.07
    dda
    0.07
    inize
    0.07
    ائز
    0.07
    Activations Density 0.075%

    No Known Activations