© 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. 103882
    Prev
    Next
    INDEX
    Explanations

    phrases related to searching for or sourcing products and ingredients

    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
    fork
    -0.06
    oru
    -0.06
    geist
    -0.05
     publishing
    -0.05
    èĬ
    -0.05
     Svens
    -0.05
     fork
    -0.05
    NÄ°
    -0.05
    orz
    -0.05
    inke
    -0.05
    POSITIVE LOGITS
    пов
    0.07
    ixo
    0.07
    èĬĤ
    0.07
    央
    0.07
    obsolete
    0.07
    agram
    0.07
    кÑĥп
    0.07
     yoksa
    0.07
    éļIJ
    0.07
     Newtown
    0.07
    Activations Density 0.012%

    No Known Activations