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

    Neuronpedia

    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. 17-LLAMASCOPE-RES-131K
    11. 56978
    Prev
    Next
    INDEX
    Explanations

    references to specific people and their actions

    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
    affle
    -0.08
    ponsors
    -0.07
    ennen
    -0.07
    isku
    -0.06
    Themes
    -0.06
    alsex
    -0.06
    boru
    -0.06
    anta
    -0.06
     presentation
    -0.06
    atica
    -0.06
    POSITIVE LOGITS
     joining
    0.10
     Join
    0.09
     join
    0.08
    joining
    0.08
     worked
    0.08
     contract
    0.08
     participation
    0.08
    worked
    0.07
     JOIN
    0.07
     contrato
    0.07
    Activations Density 0.029%

    No Known Activations