© 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. 4619
    Prev
    Next
    INDEX
    Explanations

    requests for user engagement or comments

    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
    azor
    -0.08
    uchs
    -0.07
    adir
    -0.07
    abbit
    -0.07
    üstü
    -0.07
    ัย
    -0.07
    _FOREACH
    -0.07
    abaj
    -0.07
    ÑĢами
    -0.07
    ynet
    -0.07
    POSITIVE LOGITS
     flushed
    0.06
    /loose
    0.06
    ãĥ³ãĥĸ
    0.06
     Gates
    0.06
     Hitch
    0.06
    ÑĢÑĥб
    0.05
     gastr
    0.05
     Mich
    0.05
    wright
    0.05
     hit
    0.05
    Activations Density 0.000%

    No Known Activations