Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    © Neuronpedia 2025
    Privacy & TermsBlogGitHubSlackTwitterContact
    1. Home
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 22-LLAMASCOPE-RES-131K
    6. 4756
    Prev
    Next
    INDEX
    Explanations

    references to institutional roles and their associated actions

    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
     sơ
    -0.07
    ilog
    -0.07
    áli
    -0.06
    ä½³
    -0.06
    hil
    -0.06
    aines
    -0.06
     setC
    -0.06
    ICS
    -0.06
    aller
    -0.06
    ÏĦÏİ
    -0.06
    POSITIVE LOGITS
     Dean
    0.17
     dean
    0.17
    Dean
    0.16
     Prov
    0.15
     prov
    0.15
     vice
    0.15
     Vice
    0.14
    Prov
    0.14
     university
    0.14
     chancellor
    0.14
    Activations Density 0.124%

    No Known Activations