© 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. 16190
    Prev
    Next
    INDEX
    Explanations

    mathematical or programming syntax elements

    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
    anh
    -0.07
    ãĥ¬ãĤ¹
    -0.06
    cons
    -0.06
    ong
    -0.06
    839
    -0.06
    stdClass
    -0.06
    WI
    -0.06
    enia
    -0.06
    756
    -0.06
    ongo
    -0.06
    POSITIVE LOGITS
     norge
    0.06
    üle
    0.06
     gent
    0.06
    Ãĭ
    0.06
     jenter
    0.06
     tiener
    0.06
    ftime
    0.06
    ivate
    0.06
    chin
    0.06
    ceased
    0.05
    Activations Density 0.000%

    No Known Activations