© 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. 104487
    Prev
    Next
    INDEX
    Explanations

    negative assessments or measurements in various contexts

    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
    raki
    -0.07
    errupted
    -0.07
     Ashe
    -0.07
    iddet
    -0.07
    anzeigen
    -0.06
    olen
    -0.06
    gross
    -0.06
    heimer
    -0.06
    jspx
    -0.06
    алов
    -0.06
    POSITIVE LOGITS
     zero
    0.15
    zero
    0.12
     Zero
    0.12
     completely
    0.11
     ZERO
    0.11
     nil
    0.10
    -zero
    0.10
     none
    0.10
    Zero
    0.10
    ZERO
    0.10
    Activations Density 0.023%

    No Known Activations