© 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. 78203
    Prev
    Next
    INDEX
    Explanations

    geographic locations and associated entities

    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
    oka
    -0.08
    idian
    -0.08
     coke
    -0.07
    Ale
    -0.07
    agara
    -0.07
    aginator
    -0.07
    Elf
    -0.07
    aker
    -0.07
    ains
    -0.07
    quier
    -0.07
    POSITIVE LOGITS
     Am
    0.08
    ily
    0.07
    Am
    0.07
     amy
    0.06
     am
    0.06
     Enc
    0.06
     Aly
    0.06
     Lon
    0.06
    Lon
    0.06
    amy
    0.06
    Activations Density 0.031%

    No Known Activations