© 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. 17-LLAMASCOPE-RES-131K
    11. 124975
    Prev
    Next
    INDEX
    Explanations

    statements regarding security and efficiency in technology-related contexts

    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
     tact
    -0.07
     mans
    -0.06
    enga
    -0.06
    PMC
    -0.06
    br
    -0.06
    æĦıæĢĿ
    -0.06
    _enable
    -0.06
    des
    -0.06
     Sie
    -0.06
    é¡»
    -0.06
    POSITIVE LOGITS
    osate
    0.07
    à¸ķา
    0.07
     potential
    0.07
    SEX
    0.07
    aec
    0.07
    ppe
    0.07
    èĢ
    0.06
    simp
    0.06
    ried
    0.06
    éré
    0.06
    Activations Density 0.032%

    No Known Activations