© 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. 104013
    Prev
    Next
    INDEX
    Explanations

    proper nouns relating to organizations and places

    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
    undos
    -0.07
     a
    -0.07
     cann
    -0.06
    (JS
    -0.06
    ãĤĽ
    -0.06
    Ìģt
    -0.06
    soever
    -0.06
     éĦ
    -0.06
    erson
    -0.06
    ÙijÙĩ
    -0.06
    POSITIVE LOGITS
    eum
    0.08
    dddd
    0.07
    /Edit
    0.07
    eniable
    0.07
    lez
    0.07
    ela
    0.06
    dad
    0.06
    TED
    0.06
    alian
    0.06
    ania
    0.06
    Activations Density 0.039%

    No Known Activations