© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. OpenMOSS · Llama Scope: SAEs for Llama-3.1-8B
    5. Llama3.1-8B (Base)
    7. Residual Stream
    9. 22-LLAMASCOPE-RES-131K
    11. 3696
    Prev
    Next
    INDEX
    Explanations

    references to large-scale entities or notable individuals in various contexts

    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
     Tu
    -0.06
    illus
    -0.06
    ifice
    -0.06
    ilerek
    -0.06
     harm
    -0.06
    idal
    -0.06
    ãĥ¼ãĥ«
    -0.06
     Wo
    -0.06
    alchemy
    -0.05
     Nej
    -0.05
    POSITIVE LOGITS
     names
    0.13
     name
    0.12
    -name
    0.12
     Names
    0.10
     hitters
    0.10
     hits
    0.10
    -names
    0.10
     Name
    0.10
    names
    0.09
     hitter
    0.09
    Activations Density 0.016%

    No Known Activations