© 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. 79082
    Prev
    Next
    INDEX
    Explanations

    phrases related to non-profit organizations, their impact, and various classifications or terms concerning them

    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
    оÑĢож
    -0.07
    acf
    -0.06
    iÄħ
    -0.06
    ERING
    -0.06
     thing
    -0.06
    aters
    -0.06
     to
    -0.06
    åĨ
    -0.06
    riter
    -0.06
    cad
    -0.06
    POSITIVE LOGITS
     extent
    0.16
     detriment
    0.15
    extent
    0.11
     extents
    0.11
     tune
    0.11
    venge
    0.10
     liking
    0.09
    ogle
    0.09
    gether
    0.09
     fruition
    0.09
    Activations Density 0.507%

    No Known Activations