© 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. 17-LLAMASCOPE-RES-131K
    6. 82382
    Prev
    Next
    INDEX
    Explanations

    terms related to business and finance

    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
    еви
    -0.06
    -origin
    -0.06
    oti
    -0.06
     Kerr
    -0.06
     Alv
    -0.06
    nee
    -0.05
    .datab
    -0.05
    alnız
    -0.05
    شاء
    -0.05
    Plain
    -0.05
    POSITIVE LOGITS
     such
    0.07
    å¦Ĥ
    0.07
    ä¾ĭå¦Ĥ
    0.07
    azy
    0.07
    such
    0.07
    abaj
    0.07
     жиз
    0.07
    igan
    0.06
     like
    0.06
    زÛĮ
    0.06
    Activations Density 0.039%

    No Known Activations