© 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. 61098
    Prev
    Next
    INDEX
    Explanations

    sentences that express contrast or conditional statements

    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
    ucha
    -0.06
    ASM
    -0.06
    Stamp
    -0.06
    antis
    -0.06
     promise
    -0.06
    illo
    -0.06
    æĮ¯
    -0.06
    çĶŁåij½
    -0.06
    گرد
    -0.06
    bable
    -0.06
    POSITIVE LOGITS
     competition
    0.07
     Competition
    0.07
    ervals
    0.07
    competition
    0.07
     foc
    0.07
    ripper
    0.07
    รม
    0.06
     Wich
    0.06
     competit
    0.06
     busiest
    0.06
    Activations Density 0.025%

    No Known Activations