© 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. 76700
    Prev
    Next
    INDEX
    Explanations

    instances of programming and coding references

    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
    ursal
    -0.07
    legalArgumentException
    -0.07
    geist
    -0.07
    eea
    -0.07
     Sweet
    -0.07
    quette
    -0.07
    immer
    -0.07
    /gif
    -0.07
    ezi
    -0.07
    Stamped
    -0.07
    POSITIVE LOGITS
    :↵
    0.07
    енка
    0.07
    :↵↵
    0.06
     tow
    0.06
    ecast
    0.06
    chod
    0.06
    ï¼ļ↵
    0.06
     :↵
    0.05
    uitka
    0.05
    osa
    0.05
    Activations Density 0.012%

    No Known Activations