© 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
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 17-LLAMASCOPE-RES-131K
    11. 17161
    Prev
    Next
    INDEX
    Explanations

    requests and desires expressed in the text

    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
    baugh
    -0.08
    ÏħÏĦÏĮ
    -0.08
    ugins
    -0.08
    ãģ°ãģĭãĤĬ
    -0.08
    ulares
    -0.07
    Ìī
    -0.07
     seins
    -0.07
    ãĤ¤ãĥ³ãĥĪ
    -0.07
     Fuse
    -0.07
    _Lean
    -0.07
    POSITIVE LOGITS
    IJ
    0.07
     grandchildren
    0.06
    _options
    0.06
    axe
    0.06
     proced
    0.06
    able
    0.06
     progen
    0.06
    bone
    0.06
    -options
    0.05
     changes
    0.05
    Activations Density 0.020%

    No Known Activations