© 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. 15-LLAMASCOPE-RES-131K
    11. 90703
    Prev
    Next
    INDEX
    Explanations

    contrasting ideas or statements about characters and their relationships

    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
    rens
    -0.07
    ahn
    -0.06
    éIJµ
    -0.06
    едÑĮ
    -0.06
    rupa
    -0.06
    .defaults
    -0.06
    irc
    -0.06
    ëŀ
    -0.06
    ripple
    -0.06
    ÑĢиÑĤи
    -0.06
    POSITIVE LOGITS
     alike
    0.17
    depending
    0.15
     depending
    0.14
     whichever
    0.13
     respectively
    0.13
    ichever
    0.12
     tùy
    0.10
     equally
    0.10
    depends
    0.10
     Depends
    0.10
    Activations Density 0.185%

    No Known Activations