© 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. 2439
    Prev
    Next
    INDEX
    Explanations

    references to important academic works and their impact on a field

    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
    bere
    -0.07
    licant
    -0.07
    mah
    -0.07
     Detail
    -0.06
     Chi
    -0.06
    hower
    -0.06
     theor
    -0.06
    akat
    -0.06
     mah
    -0.06
    μαÏĦο
    -0.06
    POSITIVE LOGITS
    ırak
    0.07
    ÑĪиб
    0.07
    شتÙĩ
    0.06
    .herokuapp
    0.06
     disarm
    0.06
     misplaced
    0.06
     nond
    0.06
     Lub
    0.06
     Occ
    0.06
     aficion
    0.06
    Activations Density 0.015%

    No Known Activations