© 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. 124871
    Prev
    Next
    INDEX
    Explanations

    criticisms regarding food quality and health

    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
     nÄĥ
    -0.08
    代
    -0.08
    letcher
    -0.08
    imli
    -0.07
    urtles
    -0.07
    alama
    -0.07
    atre
    -0.07
    ngth
    -0.07
    ntp
    -0.07
    ifr
    -0.07
    POSITIVE LOGITS
    484
    0.06
     &
    0.06
     âģ
    0.06
    âĢħ
    0.06
    888
    0.06
    697
    0.05
    513
    0.05
    084
    0.05
    ãĥ¥ãĥ¼
    0.05
    444
    0.05
    Activations Density 0.008%

    No Known Activations