© 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. 69803
    Prev
    Next
    INDEX
    Explanations

    mentions of the word "business" and related terms

    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
    ohana
    -0.08
    isher
    -0.08
    ucket
    -0.07
    herit
    -0.07
    çĹĩ
    -0.07
    ãģĬãĤĬ
    -0.07
    ewis
    -0.07
    éIJĺ
    -0.07
    quo
    -0.07
    usp
    -0.07
    POSITIVE LOGITS
    people
    0.08
    woman
    0.07
    (es
    0.07
    person
    0.07
    ëªħ
    0.07
    -government
    0.07
    wide
    0.07
    мен
    0.06
    plan
    0.06
    ipple
    0.06
    Activations Density 0.045%

    No Known Activations