© 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. 15-LLAMASCOPE-RES-131K
    11. 88955
    Prev
    Next
    INDEX
    Explanations

    instances of interaction or relationships between individuals

    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
    omor
    -0.07
    oke
    -0.06
    PMC
    -0.06
    roj
    -0.06
    ogan
    -0.06
    umo
    -0.06
    andle
    -0.06
     Moines
    -0.06
    och
    -0.06
     HÃłnh
    -0.06
    POSITIVE LOGITS
     others
    0.13
     fellow
    0.13
     Others
    0.11
    others
    0.10
     other
    0.10
     another
    0.10
    Others
    0.10
    (other
    0.10
     åħ¶ä»ĸ
    0.09
    缸æīĭ
    0.09
    Activations Density 0.111%

    No Known Activations