© 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. 17-LLAMASCOPE-RES-131K
    11. 85119
    Prev
    Next
    INDEX
    Explanations

    phrases indicating approval or consent related to various entities or processes

    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
    meli
    -0.08
    ÏĥÏĩ
    -0.08
    klä
    -0.07
    ì¤Ħ
    -0.07
    unate
    -0.07
     offen
    -0.07
    æķ¢
    -0.07
    ¥IJ
    -0.07
    ÅĻes
    -0.07
    hani
    -0.07
    POSITIVE LOGITS
     both
    0.10
     authorities
    0.09
    both
    0.07
     all
    0.07
     BOTH
    0.06
     majority
    0.06
     everyone
    0.06
     author
    0.06
     relevant
    0.06
    ient
    0.05
    Activations Density 0.020%

    No Known Activations