© 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. 90895
    Prev
    Next
    INDEX
    Explanations

    phrases that emphasize addition or enumeration

    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
    atter
    -0.06
    indle
    -0.06
     ath
    -0.06
    θμ
    -0.06
    638
    -0.06
    621
    -0.06
    639
    -0.06
    ata
    -0.06
    oto
    -0.06
     Andr
    -0.06
    POSITIVE LOGITS
    æİĴ
    0.07
    cko
    0.07
    ctl
    0.06
    hra
    0.06
     hosts
    0.06
    agrams
    0.06
    phin
    0.06
    oret
    0.06
    ories
    0.06
    inct
    0.06
    Activations Density 0.039%

    No Known Activations