© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports 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. 126402
    Prev
    Next
    INDEX
    Explanations

    references to moral judgment and the concept of abominations

    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
    ulace
    -0.07
    lenen
    -0.07
    Å¡em
    -0.07
    iyatı
    -0.06
    imenti
    -0.06
     downstream
    -0.06
    út
    -0.06
    alfa
    -0.06
    readcr
    -0.06
    .respond
    -0.06
    POSITIVE LOGITS
    çĬ
    0.07
     Bai
    0.06
    (rad
    0.06
     horn
    0.06
    ļ
    0.06
    ẹ
    0.06
     retract
    0.06
     Neh
    0.06
    sett
    0.06
    .scenes
    0.06
    Activations Density 0.002%

    No Known Activations