© 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. 59244
    Prev
    Next
    INDEX
    Explanations

    references to the concept of "aftermath," particularly in relation to significant events or consequences

    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
    zelf
    -0.08
     Fut
    -0.07
    hazi
    -0.07
    isable
    -0.07
     baÅŁÄ±na
    -0.07
    åŃ£
    -0.07
    rzy
    -0.07
    bons
    -0.06
     Hind
    -0.06
    abeth
    -0.06
    POSITIVE LOGITS
    물ìĿĦ
    0.08
    -effects
    0.08
    ioned
    0.07
     Effects
    0.07
    wards
    0.07
     effects
    0.07
    effects
    0.07
    WARD
    0.07
    ille
    0.07
     confusion
    0.07
    Activations Density 0.006%

    No Known Activations