© 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. 15760
    Prev
    Next
    INDEX
    Explanations

    words related to the treatment and rights of vulnerable populations

    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
     itself
    -0.13
    abbage
    -0.08
    ä¹ĭä¸Ģ
    -0.07
    inia
    -0.07
     Ñıке
    -0.07
    udoku
    -0.07
     коÑĤоÑĢое
    -0.07
    ersh
    -0.07
     StringBuffer
    -0.07
    _IOC
    -0.06
    POSITIVE LOGITS
     themselves
    0.13
     their
    0.10
    Their
    0.10
     Their
    0.10
     whom
    0.09
    their
    0.09
     who
    0.08
     leurs
    0.08
     leur
    0.07
     иÑħ
    0.07
    Activations Density 0.056%

    No Known Activations