© 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. 39376
    Prev
    Next
    INDEX
    Explanations

    references to agents or actors that play a role in various contexts or narratives

    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
    keit
    -0.09
    erdem
    -0.08
     olsa
    -0.08
    eming
    -0.08
    /preferences
    -0.08
    oming
    -0.08
    ën
    -0.08
    speaker
    -0.07
    eren
    -0.07
    river
    -0.07
    POSITIVE LOGITS
     provoc
    0.12
    ives
    0.07
    uality
    0.07
    elli
    0.07
     Ost
    0.07
    iated
    0.07
    .Agent
    0.07
    ura
    0.07
    ive
    0.07
     Lone
    0.07
    Activations Density 0.010%

    No Known Activations