© 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. 28379
    Prev
    Next
    INDEX
    Explanations

    numerical values and symbols related to formatting or syntax in coding

    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
    ikal
    -0.08
    ût
    -0.08
    DbType
    -0.08
    ucher
    -0.07
    ept
    -0.07
    reds
    -0.07
    ibraries
    -0.07
    piler
    -0.07
    gars
    -0.07
    oby
    -0.07
    POSITIVE LOGITS
    ết
    0.06
     Sunrise
    0.06
     Strict
    0.06
     Carolyn
    0.06
     Horny
    0.05
     RU
    0.05
     Tiles
    0.05
    ãĥªãĤ«
    0.05
    ÑĢÑĥб
    0.05
     Brick
    0.05
    Activations Density 0.001%

    No Known Activations