© 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. 106063
    Prev
    Next
    INDEX
    Explanations

    names of places and geographic locations

    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
    aktu
    -0.09
    vailable
    -0.08
     ><?
    -0.08
    ocale
    -0.07
    elpers
    -0.07
    nock
    -0.07
    ppe
    -0.07
    drv
    -0.07
    exus
    -0.07
    duino
    -0.07
    POSITIVE LOGITS
     village
    0.07
    onica
    0.06
     Chaos
    0.06
     Upper
    0.06
     Village
    0.06
     DISCLAIMS
    0.05
    otation
    0.05
    um
    0.05
    stage
    0.05
     lying
    0.05
    Activations Density 0.004%

    No Known Activations