© 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. 41198
    Prev
    Next
    INDEX
    Explanations

    conversational phrases or cues related to sharing opinions and experiences

    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
    коÑĤ
    -0.08
    .setViewport
    -0.07
    adiens
    -0.07
    ãĥĪãĥª
    -0.07
    vier
    -0.07
     giác
    -0.07
    orgot
    -0.07
    berman
    -0.07
     BÄĽ
    -0.07
    pher
    -0.07
    POSITIVE LOGITS
    iem
    0.06
     net
    0.06
    0.06
     Alban
    0.06
    ollo
    0.05
     Hel
    0.05
    785
    0.05
     my
    0.05
    ha
    0.05
    /cms
    0.05
    Activations Density 0.025%

    No Known Activations