© 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 EvalsExportsAPI Community BlogPrivacy & TermsContact
    1. Home
    3. DeepSeek-R1-Dist-Llama-8B
    5. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    7. 28301
    Prev
    Next
    INDEX
    Explanations

    words that express benefits

    oai_token-act-pair · gemini-2.0-flash
    New Auto-Interp
    Top Features by Cosine Similarity
    Configuration
    fnlp/Llama-Scope-R1-Distill/400M-Slimpajama-400M-OpenR1-Math-220k/L21R
    Prompts (Dashboard)
    24,576 prompts, 128 tokens each
    Dataset (Dashboard)
    Hzfinfdu/SlimPajama-3B and open-r1/OpenR1-Math-220k
    Features
    32,768
    Data Type
    float32
    Hook Name
    blocks.21.hook_resid_post
    Architecture
    jumprelu
    Context Size
    1,024
    Dataset
    cerebras/SlimPajama-627B
    Embeds
    IFrame
    Link
    Not in Any Lists

    No Comments

    Negative Logits
    ilde
    -0.06
    Binder
    -0.06
    acious
    -0.06
    icity
    -0.06
    ativ
    -0.06
    adow
    -0.06
    à¹Īà¸ĩà¸Ĥ
    -0.06
    oton
    -0.05
    æ³ī
    -0.05
    HL
    -0.05
    POSITIVE LOGITS
     benefits
    0.28
     benefit
    0.27
     Benefits
    0.22
    Benefits
    0.20
     Benefit
    0.20
    benef
    0.19
     value
    0.18
     beneficial
    0.18
    value
    0.16
     benefited
    0.16
    Activations Density 0.026%

    No Known Activations