© 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. 54397
    Prev
    Next
    INDEX
    Explanations

    indications of programming errors or issues in technical contexts

    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
    виж
    -0.06
    uner
    -0.06
    alis
    -0.06
    ÃŃrk
    -0.06
    opot
    -0.06
    ساÙĦ
    -0.06
     MessageBoxIcon
    -0.06
    ]âĢı
    -0.05
     sobie
    -0.05
    craft
    -0.05
    POSITIVE LOGITS
     vibration
    0.07
    _PROTO
    0.06
     Prom
    0.06
     Frames
    0.06
    _trampoline
    0.06
    chedulers
    0.06
    ourg
    0.06
    иÑĨин
    0.06
    sko
    0.06
     Thunder
    0.06
    Activations Density 0.000%

    No Known Activations