© 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. 61277
    Prev
    Next
    INDEX
    Explanations

    references to social media and technology usage

    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
     mold
    -0.06
    No
    -0.06
     Oaks
    -0.06
    ág
    -0.06
    As
    -0.06
    IV
    -0.06
    ock
    -0.06
    PR
    -0.05
     poison
    -0.05
     flesh
    -0.05
    POSITIVE LOGITS
     ninh
    0.09
    è¾°
    0.09
     cach
    0.08
    åĴ¨
    0.08
    istrovstvÃŃ
    0.07
    CREEN
    0.07
    ãģĻãĤĮãģ°
    0.07
    IALIZED
    0.07
    èķī
    0.07
    STYPE
    0.07
    Activations Density 0.010%

    No Known Activations