Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APICircuit TracerNEWSteerSAE EvalsExportsSlackBlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 31-LLAMASCOPE-RES-131K
    6. 44160
    Prev
    Next
    INDEX
    Explanations

    technical or mathematical terms and symbols

    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
    ðĿ
    -0.06
     Iran
    -0.06
    nbsp
    -0.05
    quiv
    -0.05
     Illinois
    -0.05
     Kabul
    -0.05
     
    -0.05
     Covid
    -0.05
    Âł
    -0.05
     opioid
    -0.05
    POSITIVE LOGITS
     british
    0.08
     tort
    0.07
     Tort
    0.07
     Barcl
    0.07
     malt
    0.07
     tortured
    0.07
    Disappear
    0.07
     TORT
    0.07
     detainees
    0.07
     torture
    0.07
    Activations Density 0.003%

    No Known Activations