© 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 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. 119314
    Prev
    Next
    INDEX
    Explanations

    occurrences of the word "was" and phrases related to ages and life events

    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
    teÅŁ
    -0.08
     dispatch
    -0.07
    ulum
    -0.07
    ÃĴ
    -0.07
    lech
    -0.07
    049
    -0.07
    _ASSUME
    -0.06
    inski
    -0.06
    ç§ĺ
    -0.06
    loses
    -0.06
    POSITIVE LOGITS
     age
    0.07
     barely
    0.07
     amp
    0.06
     an
    0.06
    ÌĤ
    0.06
     amplified
    0.06
    amm
    0.06
     Rockefeller
    0.05
     commuting
    0.05
    /am
    0.05
    Activations Density 0.007%

    No Known Activations