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

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 18127
    Prev
    Next
    INDEX
    Explanations

    verbs indicating communication or interaction between individuals

    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
     зал
    -0.07
    essler
    -0.06
    _aux
    -0.06
     Yourself
    -0.06
    çŃĴ
    -0.06
     yourself
    -0.06
    abor
    -0.06
    hus
    -0.06
    isten
    -0.06
    ire
    -0.06
    POSITIVE LOGITS
     us
    0.10
    anta
    0.07
    ogr
    0.07
    ccb
    0.07
     me
    0.06
    licant
    0.06
     Slee
    0.06
    anine
    0.06
    uos
    0.06
     nhau
    0.06
    Activations Density 0.036%

    No Known Activations