© 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. 116963
    Prev
    Next
    INDEX
    Explanations

    references to people or entities involved in events

    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
    ONGL
    -0.07
    eware
    -0.07
     Bris
    -0.07
    ewire
    -0.07
    ware
    -0.07
    WARE
    -0.07
    ahat
    -0.07
    ATAL
    -0.07
    redients
    -0.07
     GenerationType
    -0.07
    POSITIVE LOGITS
    691
    0.06
     waiting
    0.06
     vac
    0.06
    082
    0.06
    ÑĶн
    0.06
     wait
    0.06
     surve
    0.06
     handic
    0.06
     queue
    0.06
     Waiting
    0.05
    Activations Density 0.000%

    No Known Activations