© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    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. 93863
    Prev
    Next
    INDEX
    Explanations

    instances of the word "and" and similar conjunctions

    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
     diss
    -0.07
    elder
    -0.07
    .o
    -0.06
    unter
    -0.06
    exe
    -0.06
    kur
    -0.06
    amat
    -0.06
    ensus
    -0.06
    oyer
    -0.06
    iglia
    -0.05
    POSITIVE LOGITS
    although
    0.07
    éijij
    0.07
    çŀ
    0.07
     although
    0.07
    there
    0.07
     there
    0.06
    icorn
    0.06
    ithub
    0.06
    this
    0.06
    worthy
    0.06
    Activations Density 0.093%

    No Known Activations