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

    Neuronpedia

    APIAssistant AxisNEWCircuit TracerNEWSteerSAE EvalsExports Community BlogPrivacy & TermsContact
    1. Home
    2. DeepSeek-R1-Dist-Llama-8B
    3. 21-LLAMASCOPE-SLIMPJ-OPENR1-RES-32K
    4. 29670
    Prev
    Next
    INDEX
    Explanations

    mathematical formulas and calculations with numerical constants

    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
    azy
    -0.07
    £½
    -0.06
     spender
    -0.06
    utin
    -0.06
     Arithmetic
    -0.06
    762
    -0.06
     Toll
    -0.06
     Fle
    -0.06
    IGHLIGHT
    -0.06
     specifically
    -0.05
    POSITIVE LOGITS
     rather
    0.09
    ]
    0.08
    ].
    0.07
    ]↵
    0.07
    rather
    0.07
     Rather
    0.07
    plen
    0.07
    yonel
    0.07
    ].↵
    0.07
    ]:
    0.06
    Activations Density 0.058%

    No Known Activations