© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW
    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 5-LLAMASCOPE-RES-131K
    6. 125848
    Prev
    Next
    INDEX
    Explanations

    instances of movement or transition into new experiences or environments

    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
    enberg
    -0.07
    collision
    -0.07
    _quant
    -0.07
    alyze
    -0.07
    orman
    -0.07
    bst
    -0.06
     Quant
    -0.06
     æĤ
    -0.06
    perf
    -0.06
    æĿŁ
    -0.06
    POSITIVE LOGITS
    graphic
    0.06
    ctp
    0.06
    895
    0.06
     Solic
    0.06
    sz
    0.06
    .Factory
    0.06
     Abe
    0.06
     shr
    0.06
     estilo
    0.06
    ä¼ļ社
    0.06
    Activations Density 0.170%

    No Known Activations