© 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. 15-LLAMASCOPE-RES-131K
    11. 972
    Prev
    Next
    INDEX
    Explanations

    terms and roles related to creative professions or artistic endeavors

    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
    -Compatible
    -0.07
    бав
    -0.07
    aux
    -0.07
    zsche
    -0.07
    porter
    -0.07
    521
    -0.07
    aq
    -0.06
     Compatible
    -0.06
    heid
    -0.06
    (æ°´
    -0.06
    POSITIVE LOGITS
    оÑī
    0.07
    ТÐŀ
    0.06
     erst
    0.06
    ager
    0.06
    Discovery
    0.06
    eyn
    0.06
    gap
    0.06
     Discovery
    0.06
    uteur
    0.06
    ellen
    0.06
    Activations Density 0.014%

    No Known Activations