© 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. 118211
    Prev
    Next
    INDEX
    Explanations

    conditional statements or phrases related to the possibility of success or events occurring

    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
    zug
    -0.07
     either
    -0.06
    ocab
    -0.06
    auce
    -0.06
    aar
    -0.06
    eniable
    -0.06
    abay
    -0.06
     бÑĥд
    -0.06
    enson
    -0.06
    zcze
    -0.06
    POSITIVE LOGITS
     successful
    0.09
     depending
    0.09
     weather
    0.08
     correctly
    0.07
    successful
    0.07
     hitch
    0.07
    licit
    0.07
     Successful
    0.07
     successfully
    0.07
     properly
    0.07
    Activations Density 0.020%

    No Known Activations