© 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. 75272
    Prev
    Next
    INDEX
    Explanations

    references to specific individuals, particularly focusing on someone named Ethan

    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
    reta
    -0.09
    ilib
    -0.08
    vida
    -0.07
    .UIManager
    -0.07
    yun
    -0.07
    ãĥ³ãĥĨãĤ£
    -0.07
    zin
    -0.07
    ordova
    -0.07
    ends
    -0.07
    oire
    -0.07
    POSITIVE LOGITS
    andler
    0.07
    alysis
    0.07
    olic
    0.07
     Lance
    0.06
    aptic
    0.06
     unp
    0.06
     Leigh
    0.06
     uns
    0.06
    _cleanup
    0.06
    inosaur
    0.06
    Activations Density 0.003%

    No Known Activations