© 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. 55299
    Prev
    Next
    INDEX
    Explanations

    terms and phrases related to analysis and reporting data or information

    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
     tourism
    -0.07
     punch
    -0.07
    ye
    -0.07
    ADF
    -0.06
     Tourism
    -0.06
     Scatter
    -0.06
    utter
    -0.06
    urance
    -0.06
    mic
    -0.06
    çĴ
    -0.06
    POSITIVE LOGITS
     chemicals
    0.09
     Europ
    0.08
     Chemistry
    0.08
     europ
    0.07
     chemistry
    0.07
     Chem
    0.07
     europé
    0.07
     chemical
    0.07
     EU
    0.07
    Chem
    0.07
    Activations Density 0.000%

    No Known Activations