© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 9-LLAMASCOPE-RES-131K
    11. 97293
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals or groups

    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
     же
    -0.09
    ا
    -0.08
    izoph
    -0.07
    erokee
    -0.07
    heed
    -0.06
    -sided
    -0.06
    к
    -0.06
    lie
    -0.06
    mani
    -0.06
    lius
    -0.06
    POSITIVE LOGITS
    webkit
    0.08
    /of
    0.08
    /+
    0.07
    ÑĤин
    0.07
    'gc
    0.07
    ãģĬãĤĬ
    0.07
     srov
    0.07
    /-
    0.06
    ÂĢÂ
    0.06
    meer
    0.06
    Activations Density 0.127%

    No Known Activations