© 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. 128021
    Prev
    Next
    INDEX
    Explanations

    references to business establishment and investment in local economies

    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
    resco
    -0.09
    istrovstvÃŃ
    -0.09
    .updateDynamic
    -0.08
    >NN
    -0.08
    ména
    -0.08
    .ISupportInitialize
    -0.08
    ptype
    -0.07
     tolua
    -0.07
    aversable
    -0.07
    ioned
    -0.07
    POSITIVE LOGITS
     location
    0.08
     HQ
    0.07
    location
    0.07
     locating
    0.07
     Location
    0.07
    Location
    0.07
     headquarters
    0.06
    cho
    0.06
    905
    0.06
     choice
    0.06
    Activations Density 0.026%

    No Known Activations