© 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. 87627
    Prev
    Next
    INDEX
    Explanations

    concepts related to values and principles

    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
    ustil
    -0.09
    íĹĮ
    -0.08
     hete
    -0.08
     *}
    -0.08
     rež
    -0.08
    edeki
    -0.08
     cez
    -0.08
    âĢ¦âĢ¦ãĢĤ
    -0.08
    reur
    -0.08
    Ãłnh
    -0.08
    POSITIVE LOGITS
     “
    0.08
     a
    0.07
    ↵
    0.06
    Âł
    0.06
    :
    0.06
     (
    0.06
     "
    0.06
    ä¹ĭä¸Ģ
    0.06
     multiple
    0.06
     non
    0.06
    Activations Density 0.011%

    No Known Activations