© 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. 106134
    Prev
    Next
    INDEX
    Explanations

    terms related to various industries and sectors, particularly real estate, logistics, healthcare, and technology

    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
    شت
    -0.07
    roids
    -0.07
    mbH
    -0.07
    ocity
    -0.07
    IPS
    -0.07
    ERC
    -0.07
     hacks
    -0.06
    orde
    -0.06
    ourage
    -0.06
    oids
    -0.06
    POSITIVE LOGITS
     giant
    0.07
    पत
    0.07
    ioneer
    0.07
    -related
    0.07
     company
    0.07
    anos
    0.07
     stakes
    0.07
     player
    0.06
    å¸ĿåĽ½
    0.06
     maker
    0.06
    Activations Density 0.027%

    No Known Activations