© 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. 42332
    Prev
    Next
    INDEX
    Explanations

    elements of event details and logistics

    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
    ,
    -0.06
     deut
    -0.06
    liqu
    -0.06
     weekends
    -0.06
     bang
    -0.06
     initialized
    -0.05
     circuits
    -0.05
    ↵
    -0.05
     weekend
    -0.05
    á»ī
    -0.05
    POSITIVE LOGITS
    BJECT
    0.08
    ichern
    0.08
    GINE
    0.07
    çĦ¡æĸĻ
    0.07
     RSVP
    0.07
    ÎŃλ
    0.07
    dül
    0.07
    hazi
    0.07
     ëĵľë¦½ëĭĪëĭ¤
    0.07
    RS
    0.07
    Activations Density 0.014%

    No Known Activations