© 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. 88335
    Prev
    Next
    INDEX
    Explanations

    corporate and organizational names

    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
    ofil
    -0.06
    Ñģам
    -0.06
    asar
    -0.06
     jam
    -0.06
     //~
    -0.06
    iber
    -0.06
    jam
    -0.06
    éra
    -0.06
    dbContext
    -0.06
    unner
    -0.06
    POSITIVE LOGITS
    uitka
    0.08
    ież
    0.07
     disproportion
    0.07
    ÙĨز
    0.06
    OrNull
    0.06
     ìĭ±
    0.06
    lexport
    0.06
     æµģ
    0.06
     á»
    0.06
    IDTH
    0.06
    Activations Density 0.001%

    No Known Activations