© 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. 55443
    Prev
    Next
    INDEX
    Explanations

    numerical values and their formatting in various contexts

    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
    arton
    -0.07
    arhus
    -0.07
    icycle
    -0.06
    ÑĢап
    -0.06
    969
    -0.06
    énom
    -0.06
     elektrik
    -0.06
    .fe
    -0.06
    ÙĬا
    -0.06
    .sul
    -0.06
    POSITIVE LOGITS
    aders
    0.07
    âce
    0.06
     tipped
    0.06
    ฤ
    0.06
    .TODO
    0.06
     enlist
    0.06
    ÌĢ
    0.06
    ÌĪ
    0.05
     Figure
    0.05
    Ìģ
    0.05
    Activations Density 0.025%

    No Known Activations