© 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. 56493
    Prev
    Next
    INDEX
    Explanations

    phrases that indicate complex relationships or interactions

    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
     tuz
    -0.07
    ibase
    -0.07
    èĩ£
    -0.07
    noinspection
    -0.07
    renc
    -0.07
    inion
    -0.07
     kli
    -0.07
    iat
    -0.06
    heits
    -0.06
    веÑģÑĤи
    -0.06
    POSITIVE LOGITS
     itself
    0.09
     other
    0.08
    ä¹ĭä¸Ģ
    0.07
     others
    0.07
    other
    0.07
     nhau
    0.07
    others
    0.06
    çļĦéĹ®é¢ĺ
    0.06
    ãĥ³ãĤ¬
    0.06
     ãģĿãģ®ä»ĸ
    0.06
    Activations Density 0.081%

    No Known Activations