© 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. 3938
    Prev
    Next
    INDEX
    Explanations

    specific geographical or cultural references

    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
    roid
    -0.07
    oid
    -0.06
    izo
    -0.06
    eff
    -0.06
    land
    -0.06
    Äįel
    -0.06
     reclaim
    -0.06
    yum
    -0.06
    orphic
    -0.06
    ptions
    -0.06
    POSITIVE LOGITS
    kie
    0.08
    еÑĢеÑĩ
    0.08
    awah
    0.08
    ÏĦÏĮ
    0.07
    olet
    0.07
    ká
    0.07
    ký
    0.07
     ÑģебÑı
    0.07
    itel
    0.07
    çek
    0.07
    Activations Density 0.002%

    No Known Activations