© Neuronpedia 2026
    Privacy & TermsBlogGitHubSlackTwitterContact
    Neuronpedia logo - a computer chip with a rounded viewfinder border around it

    Neuronpedia

    Jacobian LensNEW
    Natural Language
    Autoencoders
    NEW    Assistant AxisNEWCircuit TracerUPDATESteerSAE EvalsExportsinterp-engineNEWAPI 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. 17442
    Prev
    Next
    INDEX
    Explanations

    sentences expressing opinions or evaluations about various subjects

    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
    ront
    -0.06
    ditor
    -0.06
    noch
    -0.06
    ãģĿãģ®
    -0.06
    itta
    -0.06
     therefore
    -0.05
    Æł
    -0.05
     Warm
    -0.05
    ë
    -0.05
    寧
    -0.05
    POSITIVE LOGITS
    worthy
    0.08
    helm
    0.08
    olini
    0.07
    deen
    0.07
    ιÏĩ
    0.07
    eos
    0.07
    oden
    0.07
     EXEMPLARY
    0.07
    apat
    0.07
    eled
    0.07
    Activations Density 0.046%

    No Known Activations