© 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
    2. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    3. Llama3.1-8B (Base)
    4. Residual Stream
    5. 17-LLAMASCOPE-RES-131K
    6. 40725
    Prev
    Next
    INDEX
    Explanations

    code structures and keywords related to API functions and method definitions

    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
    Ãłi
    -0.08
    óg
    -0.07
    itech
    -0.07
    飾
    -0.07
    netinet
    -0.07
    ivor
    -0.07
    ÙĦاØŃ
    -0.07
    -mf
    -0.07
    798
    -0.07
     extrav
    -0.07
    POSITIVE LOGITS
     set
    0.08
     Naz
    0.07
    573
    0.06
     Bang
    0.06
     Nat
    0.06
     batch
    0.06
     performed
    0.06
     sadd
    0.06
     get
    0.06
     search
    0.06
    Activations Density 0.033%

    No Known Activations