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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 87614
    Prev
    Next
    INDEX
    Explanations

    content related to health and hygiene products

    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
     Tray
    -0.07
     tray
    -0.07
    otto
    -0.07
     trays
    -0.06
     society
    -0.06
    leur
    -0.06
     Zuk
    -0.06
    antics
    -0.06
     stylesheet
    -0.06
     trunc
    -0.06
    POSITIVE LOGITS
     kits
    0.09
     essentials
    0.08
    hq
    0.08
     Essentials
    0.07
     kit
    0.07
     Kits
    0.07
    landa
    0.07
    ooks
    0.07
    -kit
    0.07
    zcze
    0.06
    Activations Density 0.014%

    No Known Activations