© 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. 15-LLAMASCOPE-RES-131K
    11. 90644
    Prev
    Next
    INDEX
    Explanations

    references to livestock management and the ethical implications of animal slaughter

    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
    omik
    -0.07
    å±Ģ
    -0.07
    reative
    -0.06
    iÅŁim
    -0.06
    á»ijc
    -0.06
    ±Ð¾ÑĤ
    -0.06
     bench
    -0.06
    ìĥĿíĻľ
    -0.05
    pirit
    -0.05
    /host
    -0.05
    POSITIVE LOGITS
    ноз
    0.07
    ÙĦاÙĦ
    0.07
    ữa
    0.07
     Huck
    0.06
    .executeQuery
    0.06
    isson
    0.06
    owie
    0.06
    yme
    0.06
     SAVE
    0.06
     getItemCount
    0.06
    Activations Density 0.002%

    No Known Activations