© 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. 62221
    Prev
    Next
    INDEX
    Explanations

    phrases related to marketing and sales dynamics

    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
    ambi
    -0.07
    gew
    -0.07
    ĶåĽŀ
    -0.06
    roke
    -0.06
     lleg
    -0.06
    æĺ
    -0.06
    errer
    -0.06
     arrives
    -0.06
     billig
    -0.06
    yal
    -0.06
    POSITIVE LOGITS
     sell
    0.10
     sold
    0.09
     sells
    0.09
     sale
    0.09
     Sold
    0.08
     find
    0.08
     SOLD
    0.08
    åĭŁ
    0.08
    Sold
    0.08
     selling
    0.08
    Activations Density 0.101%

    No Known Activations